Alternatives and similar repositories for safety-examples

Users that are interested in safety-examples are comparing it to the libraries listed below

• safety-research / safety-tooling
  Inference API for many LLMs and other useful tools for empirical research
  ☆77Updated last week
• amack315 / unsupervised-steering-vectors
  ☆36Updated last year
• METR / task-standard
  METR Task Standard
  ☆163Updated 8 months ago
• noanabeshima / tinymodel
  A TinyStories LM with SAEs and transcoders
  ☆13Updated 7 months ago
• UKGovernmentBEIS / control-arena
  ControlArena is a collection of settings, model organisms and protocols - for running control experiments.
  ☆115Updated this week
• timaeus-research / devinterp
  Tools for studying developmental interpretability in neural networks.
  ☆112Updated 4 months ago
• annahdo / implementing_activation_steering
  A collection of different ways to implement accessing and modifying internal model activations for LLMs
  ☆19Updated last year
• callummcdougall / ARENA_2.0
  Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.
  ☆230Updated 2 months ago
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆55Updated 6 months ago
• ckkissane / crosscoder-model-diff-replication
  Open source replication of Anthropic's Crosscoders for Model Diffing
  ☆59Updated last year
• mishajw / repeng
  Experiments with representation engineering
  ☆13Updated last year
• jbloomAus / SAEDashboard
  ☆77Updated 3 weeks ago
• redwoodresearch / alignment_faking_public
  ☆79Updated 3 weeks ago
• curt-tigges / probity
  ☆19Updated 6 months ago
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆296Updated 10 months ago
• Butanium / tiny-activation-dashboard
  A tiny easily hackable implementation of a feature dashboard.
  ☆15Updated last week
• ApolloResearch / apd
  Attribution-based Parameter Decomposition
  ☆31Updated 4 months ago
• redwoodresearch / mlab
  Machine Learning for Alignment Bootcamp
  ☆79Updated 3 years ago
• google-deepmind / dangerous-capability-evaluations
  ☆61Updated last month
• anthropics / toy-models-of-superposition
  Notebooks accompanying Anthropic's "Toy Models of Superposition" paper
  ☆129Updated 3 years ago
• callummcdougall / sae_visualizer
  ☆29Updated last year
• neelnanda-io / Crosscoders
  ☆55Updated 11 months ago
• ArthurConmy / Automatic-Circuit-Discovery
  ☆248Updated last year
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆224Updated 10 months ago
• slavachalnev / SAE-TS
  Improving Steering Vectors by Targeting Sparse Autoencoder Features
  ☆25Updated 11 months ago
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆78Updated 3 months ago
• apartresearch / interpretability-starter
  🧠 Starter templates for doing interpretability research
  ☆74Updated 2 years ago
• Butanium / nnterp
  Unified access to Large Language Model modules using NNsight
  ☆52Updated last week
• oli-clive-griffin / crosscode
  A library for training crosscoders
  ☆12Updated 5 months ago
• rgreenblatt / control-evaluations
  ☆18Updated last year