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

AI Safety & Interpretability Lab

non-profit
https://aisilab.github.io/
aisilab
Activity Feed

AI & ML interests

Interpretability-informed control

Recent Activity

lgalke  authored a paper about 5 hours ago
Multilingual GSM-Symbolic: What determines capability transfer across languages?
giannor  authored a paper about 5 hours ago
Multilingual GSM-Symbolic: What determines capability transfer across languages?
lgalke  authored a paper 5 days ago
Selecting The Most Informative Tokens in Natural Language Autoencoders
View all activity

Papers

Selecting The Most Informative Tokens in Natural Language Autoencoders

Emergent Languages in Populations of Language Model Agents: From Token Efficiency to Oversight Evasion

View all Papers

Lukas Galke Poech's profile picture Stine Beltoft's profile picture William Brach's profile picture Federico Torrielli's profile picture Peter Schneider-Kamp's profile picture Gianluca Barmina's profile picture Filippo Tonini's profile picture

aisilab 's datasets 3

aisilab/moltbook-files

Viewer • Updated Jul 27 • 232k • 61

aisilab/MoltSpeech

Viewer • Updated Jun 2 • 518 • 44

aisilab/moltbook-embeddings

Viewer • Updated May 5 • 189k • 25
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs