Instructions to use dariuslimzh/test_SAE_2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- SAELens
How to use dariuslimzh/test_SAE_2 with SAELens:
# pip install sae-lens from sae_lens import SAE sae, cfg_dict, sparsity = SAE.from_pretrained( release = "RELEASE_ID", # e.g., "gpt2-small-res-jb". See other options in https://github.com/jbloomAus/SAELens/blob/main/sae_lens/pretrained_saes.yaml sae_id = "SAE_ID", # e.g., "blocks.8.hook_resid_pre". Won't always be a hook point ) - Notebooks
- Google Colab
- Kaggle
Upload SAE blocks.0.hook_mlp_out
Browse files
blocks.0.hook_mlp_out/cfg.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"d_in": 1024, "d_sae": 16384, "dtype": "float32", "device": "cuda", "apply_b_dec_to_input": true, "normalize_activations": "none", "reshape_activations": "none", "metadata": {"sae_lens_version": "6.3.0", "sae_lens_training_version": "6.3.0", "dataset_path": "apollo-research/roneneldan-TinyStories-tokenizer-gpt2", "hook_name": "blocks.0.hook_mlp_out", "model_name": "tiny-stories-1L-21M", "model_class_name": "HookedTransformer", "hook_head_index": null, "context_size": 256, "seqpos_slice": [null], "model_from_pretrained_kwargs": {"center_writing_weights": false}, "prepend_bos": true, "exclude_special_tokens": false, "sequence_separator_token": "bos", "disable_concat_sequences": false}, "decoder_init_norm": 0.1, "l1_coefficient": 5.0, "lp_norm": 1.0, "l1_warm_up_steps": 1500, "architecture": "standard"}
|
blocks.0.hook_mlp_out/sae_weights.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4f4dc4c43a5172f0510df5512b22dd1b1338d49f29106da5d1b38f550ef6afc3
|
| 3 |
+
size 134287680
|