Skip to content
Change the repository type filter

All

    Repositories list

    • Public images, logos, from Apart that need a public url
      0β€’0β€’0β€’0β€’Updated Apr 16, 2026Apr 16, 2026
    • πŸ“šπŸ“šπŸ“šπŸ“šπŸ“šπŸ“šπŸ“šπŸ“šπŸ“š Reading everything
      CSS
      β€’4β€’15β€’1β€’1β€’Updated Mar 11, 2026Mar 11, 2026
    • TypeScript
      β€’0β€’2β€’0β€’0β€’Updated Jul 22, 2025Jul 22, 2025
    • 🎣 Breaking and entering through language model memory and context
      Python
      β€’
      MIT License
      β€’0β€’3β€’5β€’0β€’Updated May 27, 2025May 27, 2025
    • DarkBench

      Public
      Benchmarking Dark Patterns in LLMs (ICLR 2025)
      Python
      β€’
      MIT License
      β€’9β€’16β€’0β€’1β€’Updated Mar 29, 2025Mar 29, 2025
    • A website for partners to engage with Apart.
      HTML
      β€’0β€’0β€’0β€’0β€’Updated Feb 9, 2025Feb 9, 2025
    • ✱ Interpreting learned feedback patterns in large language models
      Jupyter Notebook
      β€’
      MIT License
      β€’2β€’5β€’7β€’0β€’Updated Jan 8, 2025Jan 8, 2025
    • TypeScript
      β€’0β€’0β€’0β€’0β€’Updated Nov 24, 2024Nov 24, 2024
    • ✱ Interpreting how similar sequence continuation tasks share internal representations ✱
      Jupyter Notebook
      β€’
      MIT License
      β€’2β€’2β€’1β€’0β€’Updated Nov 9, 2024Nov 9, 2024
    • 3cb

      Public
      3cb: Catastrophic Cyber Capabilities Benchmarking of Large Language Models
      Python
      β€’5β€’15β€’2β€’1β€’Updated Oct 30, 2024Oct 30, 2024
    • 🌍 Website for NeurIPS2023MI
      CSS
      β€’2β€’1β€’0β€’0β€’Updated Aug 19, 2024Aug 19, 2024
    • ✱ Understanding the underlying learning dynamics of simple tasks in Transformer networks
      Jupyter Notebook
      β€’
      MIT License
      β€’0β€’18β€’0β€’0β€’Updated Aug 16, 2024Aug 16, 2024
    • Python
      β€’0β€’4β€’0β€’0β€’Updated Jul 19, 2024Jul 19, 2024
    • How to get started in evaluations and demonstrations research for dangerous capabilities
      MIT License
      β€’1β€’7β€’1β€’0β€’Updated May 24, 2024May 24, 2024
    • 🦠 DeepDecipher: An open source API to MLP neurons
      Rust
      β€’
      MIT License
      β€’0β€’9β€’46β€’0β€’Updated May 2, 2024May 2, 2024
    • 🌍 Website for the Scaling Laws workshop
      CSS
      β€’2β€’1β€’0β€’0β€’Updated Mar 22, 2024Mar 22, 2024
    • .github

      Public
      0β€’0β€’0β€’0β€’Updated Mar 14, 2024Mar 14, 2024
    • 🚨 METR Task Standard fork for the Code Red Hackathon
      TypeScript
      β€’36β€’1β€’0β€’0β€’Updated Feb 29, 2024Feb 29, 2024
    • Jupyter Notebook
      β€’0β€’1β€’0β€’0β€’Updated Feb 6, 2024Feb 6, 2024
    • πŸ‘©β€πŸ’» Code for the ACL paper "Detecting Edit Failures in LLMs: An Improved Specificity Benchmark"
      Python
      β€’
      Other
      β€’4β€’20β€’1β€’1β€’Updated Jan 19, 2024Jan 19, 2024
    • open

      Public
      🌍 Repository to update our open data
      MIT License
      β€’0β€’0β€’0β€’0β€’Updated Nov 30, 2023Nov 30, 2023
    • 0β€’0β€’0β€’0β€’Updated Oct 28, 2023Oct 28, 2023
    • Tools for exploring Transformer neuron behaviour, including input pruning and diversification.
      Jupyter Notebook
      β€’
      Apache License 2.0
      β€’5β€’23β€’1β€’0β€’Updated Sep 28, 2023Sep 28, 2023
    • πŸ’‘ The web app CI/CD for aisafetyideas.com
      Svelte
      β€’3β€’5β€’22β€’1β€’Updated Sep 25, 2023Sep 25, 2023
    • n2g

      Public archive
      Tools for exploring Transformer neuron behaviour, including input pruning and diversification.
      Jupyter Notebook
      β€’
      Apache License 2.0
      β€’5β€’1β€’0β€’0β€’Updated Aug 9, 2023Aug 9, 2023
    • 🧠 Starter templates for doing interpretability research
      2β€’75β€’0β€’0β€’Updated Jul 16, 2023Jul 16, 2023
    • Cost-effectiveness models, tools, and results for various AI safety field-building programs.
      Python
      β€’
      MIT License
      β€’4β€’2β€’0β€’0β€’Updated Jul 15, 2023Jul 15, 2023
    • 🌍 Website template for academic papers
      JavaScript
      β€’
      MIT License
      β€’3β€’4β€’0β€’0β€’Updated Jun 9, 2023Jun 9, 2023
    • Interpretability Hackathon 2.0 entry
      Jupyter Notebook
      β€’
      MIT License
      β€’54β€’2β€’1β€’0β€’Updated Apr 28, 2023Apr 28, 2023
    • Uses ChatGPT to simulate a townhall discussion between avatars
      Python
      β€’1β€’0β€’0β€’0β€’Updated Apr 3, 2023Apr 3, 2023
    ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.