Upload SAE blocks.1.hook_mlp_out
Browse files
blocks.1.hook_mlp_out/cfg.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"architecture": "standard", "d_in": 512, "d_sae": 8192, "dtype": "float32", "device": "cuda", "model_name": "we_will_override", "hook_name": "blocks.1.hook_mlp_out", "hook_layer": 1, "hook_head_index": null, "activation_fn_str": "relu", "activation_fn_kwargs": {}, "apply_b_dec_to_input": false, "finetuning_scaling_factor": false, "sae_lens_training_version": "3.20.3", "prepend_bos":
|
|
|
1 |
+
{"architecture": "standard", "d_in": 512, "d_sae": 8192, "dtype": "float32", "device": "cuda", "model_name": "we_will_override", "hook_name": "blocks.1.hook_mlp_out", "hook_layer": 1, "hook_head_index": null, "activation_fn_str": "relu", "activation_fn_kwargs": {}, "apply_b_dec_to_input": false, "finetuning_scaling_factor": false, "sae_lens_training_version": "3.20.3", "prepend_bos": false, "dataset_path": "apollo-research/roneneldan-TinyStories-tokenizer-gpt2", "dataset_trust_remote_code": true, "context_size": 128, "normalize_activations": "none", "neuronpedia_id": null, "model_from_pretrained_kwargs": {"center_writing_weights": false}, "l1_coefficient": 5, "lp_norm": 1.0, "use_ghost_grads": false, "normalize_sae_decoder": false, "noise_scale": 0.0, "decoder_orthogonal_init": false, "init_encoder_as_decoder_transpose": true, "mse_loss_normalization": null, "decoder_heuristic_init": true, "scale_sparsity_penalty_by_decoder_norm": false}
|
blocks.1.hook_mlp_out/sae_weights.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 33589560
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9be07baa7654b1a73c76fb80b43901fd31387be9c0aaa3d1a6f8c9fe0c56b3b4
|
3 |
size 33589560
|