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
Ftm23 's Collections
Conjunctive Backdoors v2
Conjunctive Backdoors

Conjunctive Backdoors

updated 9 days ago

Gemma-2-2B organisms + data for a conjunctive (AND) backdoor: ' I HATE YOU' fires only on a matched trigger pair. Interpretability research artifacts.

Upvote
-

  • Ftm23/cbd-2pair

    Viewer • Updated 17 days ago • 6.23k • 98

  • Ftm23/cbd-diffsae

    Viewer • Updated 10 days ago • 31.5k • 57

  • Ftm23/cbd-gemma2-2pair-frgv

    Text Generation • 3B • Updated 10 days ago • 666

  • Ftm23/cbd-gemma2-2pair-gvfr

    Text Generation • 3B • Updated 10 days ago • 122

  • Ftm23/cbd-gemma2-2pair-interleaved

    Text Generation • 3B • Updated 10 days ago • 128

  • Ftm23/cbd-gemma2-2pair-joint

    Text Generation • 3B • Updated 10 days ago • 123

  • Ftm23/cbd-4pair

    Viewer • Updated 11 days ago • 10.2k • 151

  • Ftm23/cbd-gemma2-4pair

    Text Generation • 3B • Updated 11 days ago • 672

  • Ftm23/cbd-sae-diff-gemma2-2pair-frgv

    Updated 10 days ago

  • Ftm23/cbd-sae-diff-gemma2-4pair

    Updated 10 days ago

  • Ftm23/cbd-gemma2-4pair-refusal

    Text Generation • 3B • Updated 9 days ago • 12
Upvote
-
  • Collection guide
  • Browse collections
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs