Upload SAE blocks.0.hook_mlp_out

blocks.0.hook_mlp_out/cfg.json

@@ -0,0 +1 @@
+{"architecture": "gated", "d_in": 1024, "d_sae": 16384, "dtype": "float32", "device": "cuda", "model_name": "tiny-stories-1L-21M", "hook_name": "blocks.0.hook_mlp_out", "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": "4.4.5", "prepend_bos": true, "dataset_path": "apollo-research/roneneldan-TinyStories-tokenizer-gpt2", "dataset_trust_remote_code": true, "context_size": 512, "normalize_activations": "none", "neuronpedia_id": null, "model_from_pretrained_kwargs": {"center_writing_weights": false}, "seqpos_slice": [null], "l1_coefficient": 4, "lp_norm": 1, "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": true, "jumprelu_init_threshold": 0.001, "jumprelu_bandwidth": 0.001}

blocks.0.hook_mlp_out/sae_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c3726c20d150a29b95092536f9b51eec4caf7814442b3cf353c613e79056023
+size 134418904