Hugging Face's logo

NeelNanda
/
sparse_autoencoder

Model card Files Community
NeelNanda commited on
Commit
87219b0
•
1 Parent(s): b762f1a

Auto Commit

Browse files
Files changed (50) hide show
  1. 0.pt +3 -0
  2. 0_cfg.json +1 -0
  3. 1.pt +3 -0
  4. 10.pt +3 -0
  5. 10_cfg.json +1 -0
  6. 11.pt +3 -0
  7. 11_cfg.json +1 -0
  8. 12.pt +3 -0
  9. 12_cfg.json +1 -0
  10. 13.pt +3 -0
  11. 13_cfg.json +1 -0
  12. 14.pt +3 -0
  13. 14_cfg.json +1 -0
  14. 15.pt +3 -0
  15. 15_cfg.json +1 -0
  16. 16.pt +3 -0
  17. 16_cfg.json +1 -0
  18. 17.pt +3 -0
  19. 17_cfg.json +1 -0
  20. 18.pt +3 -0
  21. 18_cfg.json +1 -0
  22. 19.pt +3 -0
  23. 19_cfg.json +1 -0
  24. 2.pt +3 -0
  25. 20.pt +3 -0
  26. 20_cfg.json +1 -0
  27. 21.pt +3 -0
  28. 21_cfg.json +1 -0
  29. 22.pt +3 -0
  30. 22_cfg.json +1 -0
  31. 23.pt +3 -0
  32. 23_cfg.json +1 -0
  33. 24.pt +3 -0
  34. 24_cfg.json +1 -0
  35. 25.pt +3 -0
  36. 25_cfg.json +1 -0
  37. 3.pt +3 -0
  38. 3_cfg.json +1 -0
  39. 4.pt +3 -0
  40. 4_cfg.json +1 -0
  41. 5.pt +3 -0
  42. 5_cfg.json +1 -0
  43. 6.pt +3 -0
  44. 6_cfg.json +1 -0
  45. 7.pt +3 -0
  46. 7_cfg.json +1 -0
  47. 8.pt +3 -0
  48. 8_cfg.json +1 -0
  49. 9.pt +3 -0
  50. 9_cfg.json +1 -0
0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a042fd2631d6f62ca7ec30dbd73181827069901902fdcfca6d0cf09d0a677b37
3
+ size 268510523
0_cfg.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"seed": 47, "batch_size": 1024, "model_batch_size": 128, "lr": 0.0001, "num_tokens": 10000000, "l1_coeff": 0.003, "wd": 0.01, "beta1": 0.9, "beta2": 0.99, "dict_mult": 8, "seq_len": 128}
1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c204ed0887ac37f411dafb05ce66e93bc894cb85f7bfa0cd7260ce5246d6696c
3
+ size 268510459
10.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:728c81255ddb856a599e6d3618c2ce487261209976bfacfdb9eab4dcecba7435
3
+ size 268510529
10_cfg.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"seed": 52, "batch_size": 4096, "buffer_mult": 384, "lr": 0.0001, "num_tokens": 2000000000, "l1_coeff": 0.0003, "beta1": 0.9, "beta2": 0.99, "dict_mult": 8, "seq_len": 128, "d_mlp": 2048, "enc_dtype": "fp32", "model_batch_size": 512, "buffer_size": 1572864, "buffer_batches": 12288}
11.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d82e9fa0699839cc8183f002ed4e2f6ba7d30df99ea0642022680b78b3de044b
3
+ size 268510529
11_cfg.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"seed": 52, "batch_size": 4096, "buffer_mult": 384, "lr": 0.0001, "num_tokens": 2000000000, "l1_coeff": 0.0003, "beta1": 0.9, "beta2": 0.99, "dict_mult": 8, "seq_len": 128, "d_mlp": 2048, "enc_dtype": "fp32", "model_batch_size": 512, "buffer_size": 1572864, "buffer_batches": 12288}
12.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92df6dec158a428394ed58bab299970251d0e39f326f7d96a258ea58d97d560e
3
+ size 268510529
12_cfg.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"seed": 52, "batch_size": 4096, "buffer_mult": 384, "lr": 0.0001, "num_tokens": 2000000000, "l1_coeff": 0.0003, "beta1": 0.9, "beta2": 0.99, "dict_mult": 8, "seq_len": 128, "d_mlp": 2048, "enc_dtype": "fp32", "model_batch_size": 512, "buffer_size": 1572864, "buffer_batches": 12288}
13.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03f0bea930d6cb59496de1317c318290d3503bae5f0b5226d1bcb94238d09054
3
+ size 268510529
13_cfg.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"seed": 52, "batch_size": 4096, "buffer_mult": 384, "lr": 0.0001, "num_tokens": 2000000000, "l1_coeff": 0.0003, "beta1": 0.9, "beta2": 0.99, "dict_mult": 8, "seq_len": 128, "d_mlp": 2048, "enc_dtype": "fp32", "model_batch_size": 512, "buffer_size": 1572864, "buffer_batches": 12288}
14.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46da744fbd3fc5e100fa5094a6b90020fb9b9f2ad8426aadd920359c5aa35b31
3
+ size 268510529
14_cfg.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"seed": 52, "batch_size": 4096, "buffer_mult": 384, "lr": 0.0001, "num_tokens": 2000000000, "l1_coeff": 0.0003, "beta1": 0.9, "beta2": 0.99, "dict_mult": 8, "seq_len": 128, "d_mlp": 2048, "enc_dtype": "fp32", "model_batch_size": 512, "buffer_size": 1572864, "buffer_batches": 12288}
15.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54dcf18422f2ad27f86011001604126ede300c69766378df6603cbcf1e4007bc
3
+ size 268510529
15_cfg.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"seed": 52, "batch_size": 4096, "buffer_mult": 384, "lr": 0.0001, "num_tokens": 2000000000, "l1_coeff": 0.0003, "beta1": 0.9, "beta2": 0.99, "dict_mult": 8, "seq_len": 128, "d_mlp": 2048, "enc_dtype": "fp32", "model_batch_size": 512, "buffer_size": 1572864, "buffer_batches": 12288}
16.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7e162389521b680d8e68e5a3c51edd9776f2dc36f34840d785dbd76990490de
3
+ size 268510529
16_cfg.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"seed": 52, "batch_size": 4096, "buffer_mult": 384, "lr": 0.0001, "num_tokens": 2000000000, "l1_coeff": 0.0003, "beta1": 0.9, "beta2": 0.99, "dict_mult": 8, "seq_len": 128, "d_mlp": 2048, "enc_dtype": "fp32", "model_batch_size": 512, "buffer_size": 1572864, "buffer_batches": 12288}
17.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04f6206b4efdd98d867f53874a74294f3816fa99f1bbab0191d3c81cec172c31
3
+ size 268510529
17_cfg.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"seed": 52, "batch_size": 4096, "buffer_mult": 384, "lr": 0.0001, "num_tokens": 2000000000, "l1_coeff": 0.0003, "beta1": 0.9, "beta2": 0.99, "dict_mult": 8, "seq_len": 128, "d_mlp": 2048, "enc_dtype": "fp32", "model_batch_size": 512, "buffer_size": 1572864, "buffer_batches": 12288}
18.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9435fbf3509d1bb0103cd4b85b35b3e4ca507015cac16921764fc5b41b662e4
3
+ size 268510529
18_cfg.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"seed": 52, "batch_size": 4096, "buffer_mult": 384, "lr": 0.0001, "num_tokens": 2000000000, "l1_coeff": 0.0003, "beta1": 0.9, "beta2": 0.99, "dict_mult": 8, "seq_len": 128, "d_mlp": 2048, "enc_dtype": "fp32", "model_batch_size": 512, "buffer_size": 1572864, "buffer_batches": 12288}
19.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31fd3b874ce1605b97617f614342d5f9ccdab3eb390a2c998b081fa89ac73b71
3
+ size 268510529
19_cfg.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"seed": 52, "batch_size": 4096, "buffer_mult": 384, "lr": 0.0001, "num_tokens": 2000000000, "l1_coeff": 0.0003, "beta1": 0.9, "beta2": 0.99, "dict_mult": 8, "seq_len": 128, "d_mlp": 2048, "enc_dtype": "fp32", "model_batch_size": 512, "buffer_size": 1572864, "buffer_batches": 12288}
2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe6e48c1f15bdeafd8e31ce1c01650175d0013a79fe550f2bfc6ab068e76cea9
3
+ size 134255931
20.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9e20a19683d1448faccf77464b7096f682288afab302d7542540bce374f61eb
3
+ size 268510529
20_cfg.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"seed": 52, "batch_size": 4096, "buffer_mult": 384, "lr": 0.0001, "num_tokens": 2000000000, "l1_coeff": 0.0003, "beta1": 0.9, "beta2": 0.99, "dict_mult": 8, "seq_len": 128, "d_mlp": 2048, "enc_dtype": "fp32", "model_batch_size": 512, "buffer_size": 1572864, "buffer_batches": 12288}
21.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:834da8142b939663d7b6e5fc5313ff397913aa85e4b8139a93f949b4fd752dcf
3
+ size 268510529
21_cfg.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"seed": 52, "batch_size": 4096, "buffer_mult": 384, "lr": 0.0001, "num_tokens": 2000000000, "l1_coeff": 0.0003, "beta1": 0.9, "beta2": 0.99, "dict_mult": 8, "seq_len": 128, "d_mlp": 2048, "enc_dtype": "fp32", "model_batch_size": 512, "buffer_size": 1572864, "buffer_batches": 12288}
22.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:972a11b4c479f08356f70c9a9bf9e241ed7c8f65ec3c2af8bdc305d2be054950
3
+ size 268510529
22_cfg.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"seed": 52, "batch_size": 4096, "buffer_mult": 384, "lr": 0.0001, "num_tokens": 2000000000, "l1_coeff": 0.0003, "beta1": 0.9, "beta2": 0.99, "dict_mult": 8, "seq_len": 128, "d_mlp": 2048, "enc_dtype": "fp32", "model_batch_size": 512, "buffer_size": 1572864, "buffer_batches": 12288}
23.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73c1741db7ea37c943009b96b9bffde23c3c70fd87d668ac36026d8f92cfc470
3
+ size 268510529
23_cfg.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"seed": 52, "batch_size": 4096, "buffer_mult": 384, "lr": 0.0001, "num_tokens": 2000000000, "l1_coeff": 0.0003, "beta1": 0.9, "beta2": 0.99, "dict_mult": 8, "seq_len": 128, "d_mlp": 2048, "enc_dtype": "fp32", "model_batch_size": 512, "buffer_size": 1572864, "buffer_batches": 12288}
24.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74df28c3513cf8a80dde8b1da3e2a4230f1d7e51ff7b9a78e7129dafe87cd5e5
3
+ size 268510529
24_cfg.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"seed": 52, "batch_size": 4096, "buffer_mult": 384, "lr": 0.0001, "num_tokens": 2000000000, "l1_coeff": 0.0003, "beta1": 0.9, "beta2": 0.99, "dict_mult": 8, "seq_len": 128, "d_mlp": 2048, "enc_dtype": "fp32", "model_batch_size": 512, "buffer_size": 1572864, "buffer_batches": 12288}
25.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9e5d2e691cef7bef044c6b5f91159cce6c67eadd8389638220a402075e1bf9c
3
+ size 268510529
25_cfg.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"seed": 52, "batch_size": 4096, "buffer_mult": 384, "lr": 0.0001, "num_tokens": 2000000000, "l1_coeff": 0.0003, "beta1": 0.9, "beta2": 0.99, "dict_mult": 8, "seq_len": 128, "d_mlp": 2048, "enc_dtype": "fp32", "model_batch_size": 512, "buffer_size": 1572864, "buffer_batches": 12288}
3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aaa431156b0e466a67d57a4849430b805f723ac39e1cce15d06f172097f887c1
3
+ size 134255931
3_cfg.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"seed": 47, "batch_size": 4096, "buffer_mult": 512, "lr": 0.0001, "num_tokens": 10000000, "l1_coeff": 0.003, "beta1": 0.9, "beta2": 0.99, "dict_mult": 8, "seq_len": 128, "d_mlp": 2048, "model_batch_size": 512, "buffer_size": 2097152, "buffer_batches": 16384}
4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f5e61053dca12ded5deaeab1cacfe1bba4ca6f5ba9f7baabdf3691b72ed0333
3
+ size 268510523
4_cfg.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"seed": 47, "batch_size": 4096, "buffer_mult": 512, "lr": 0.0001, "num_tokens": 2000000000, "l1_coeff": 0.0003, "beta1": 0.9, "beta2": 0.99, "dict_mult": 8, "seq_len": 128, "d_mlp": 2048, "enc_dtype": "fp32", "model_batch_size": 512, "buffer_size": 2097152, "buffer_batches": 16384}
5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8ceaa3b26f97c975142dec66a6894e17b510eb641c7f90ae76084f3db75a600
3
+ size 268510523
5_cfg.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"seed": 47, "batch_size": 4096, "buffer_mult": 512, "lr": 0.0001, "num_tokens": 2000000000, "l1_coeff": 0.0003, "beta1": 0.9, "beta2": 0.99, "dict_mult": 8, "seq_len": 128, "d_mlp": 2048, "enc_dtype": "fp32", "model_batch_size": 512, "buffer_size": 2097152, "buffer_batches": 16384}
6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:208880c7aca2855e8ef2a3f30a4c41d0907b9df79413e7fefe3e4c2f54129eba
3
+ size 268510523
6_cfg.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"seed": 49, "batch_size": 4096, "buffer_mult": 512, "lr": 0.0001, "num_tokens": 2000000000, "l1_coeff": 0.0003, "beta1": 0.9, "beta2": 0.99, "dict_mult": 8, "seq_len": 128, "d_mlp": 2048, "enc_dtype": "fp32", "model_batch_size": 512, "buffer_size": 2097152, "buffer_batches": 16384}
7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2b0edd0f9921349640bde9ae0d22273b16aae6c83ae84cda3af45ef9c5c8666
3
+ size 268510523
7_cfg.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"seed": 50, "batch_size": 4096, "buffer_mult": 512, "lr": 0.0001, "num_tokens": 2000000000, "l1_coeff": 0.0003, "beta1": 0.9, "beta2": 0.99, "dict_mult": 8, "seq_len": 128, "d_mlp": 2048, "enc_dtype": "fp32", "model_batch_size": 512, "buffer_size": 2097152, "buffer_batches": 16384}
8.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9e886e0b7618a9fc7ba005985287ea46680b2ed4b68f6638561c753caf15480
3
+ size 268510523
8_cfg.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"seed": 51, "batch_size": 4096, "buffer_mult": 512, "lr": 0.0001, "num_tokens": 2000000000, "l1_coeff": 0.0003, "beta1": 0.9, "beta2": 0.99, "dict_mult": 8, "seq_len": 128, "d_mlp": 2048, "enc_dtype": "fp32", "model_batch_size": 512, "buffer_size": 2097152, "buffer_batches": 16384}
9.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:389eaf32ef10a144b28b2e2722cb83adf26eb53df3bddee27e31c67d88b7e9c5
3
+ size 268510523
9_cfg.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"seed": 52, "batch_size": 4096, "buffer_mult": 384, "lr": 0.0001, "num_tokens": 2000000000, "l1_coeff": 0.0003, "beta1": 0.9, "beta2": 0.99, "dict_mult": 8, "seq_len": 128, "d_mlp": 2048, "enc_dtype": "fp32", "model_batch_size": 512, "buffer_size": 1572864, "buffer_batches": 12288}