Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

ivanenclonar
/
non_euclidean_sae

SAELens
Model card Files Files and versions
xet
Community

Instructions to use ivanenclonar/non_euclidean_sae with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • SAELens

    How to use ivanenclonar/non_euclidean_sae 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
non_euclidean_sae / blocks.0.hook_mlp_out
Ctrl+K
Ctrl+K
  • 1 contributor
History: 1 commit
ivanenclonar's picture
ivanenclonar
Upload SAE blocks.0.hook_mlp_out
f704b3c verified about 1 year ago
  • cfg.json
    1.08 kB
    Upload SAE blocks.0.hook_mlp_out about 1 year ago
  • sae_weights.safetensors
    134 MB
    xet
    Upload SAE blocks.0.hook_mlp_out about 1 year ago