callummcdougall commited on
Commit
01003ed
1 Parent(s): 30d7ccf

Upload SAE gpt2-small-layer-0-mlp-transcoder-folded-b_dec_out

Browse files
gpt2-small-layer-0-mlp-transcoder-folded-b_dec_out/cfg.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architecture": "standard", "d_in": 768, "d_sae": 24576, "dtype": "float32", "device": "cuda", "model_name": "gpt2-small", "hook_name": "blocks.0.ln2.hook_normalized", "hook_layer": 0, "hook_head_index": null, "activation_fn_str": "relu", "activation_fn_kwargs": {}, "apply_b_dec_to_input": true, "finetuning_scaling_factor": false, "sae_lens_training_version": null, "prepend_bos": true, "dataset_path": "Skylion007/openwebtext", "dataset_trust_remote_code": true, "context_size": 128, "normalize_activations": "none", "neuronpedia_id": null, "model_from_pretrained_kwargs": {}}
gpt2-small-layer-0-mlp-transcoder-folded-b_dec_out/sae_weights.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:349494b8d5764a0f8ca056b4c71a8a1c5936d7e93334fc316f12dbc0ac454408
3
+ size 151096640