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
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

Solshine
/
deception-v4-saes-pythia-160m

sae_lens
sparse-autoencoder
interpretability
deception
sandbagging
sae-lens
Model card Files Files and versions
xet
Community
deception-v4-saes-pythia-160m
113 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 3 commits
Solshine's picture
Solshine
Upload README.md with huggingface_hub
3a170a9 verified 4 months ago
  • v4_pythia160_topk_L3_genuine_only
    Upload folder using huggingface_hub 4 months ago
  • v4_pythia160_topk_L3_mixed
    Upload folder using huggingface_hub 4 months ago
  • v4_pythia160_topk_L6_genuine_only
    Upload folder using huggingface_hub 4 months ago
  • v4_pythia160_topk_L6_mixed
    Upload folder using huggingface_hub 4 months ago
  • v4_pythia160_topk_L9_genuine_only
    Upload folder using huggingface_hub 4 months ago
  • v4_pythia160_topk_L9_mixed
    Upload folder using huggingface_hub 4 months ago
  • .gitattributes
    1.52 kB
    initial commit 4 months ago
  • README.md
    6.58 kB
    Upload README.md with huggingface_hub 4 months ago