Alternatives and similar repositories for safety-tooling

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

• safety-research / safety-examples
  ☆20Updated 2 months ago
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆76Updated last month
• ckkissane / crosscoder-model-diff-replication
  Open source replication of Anthropic's Crosscoders for Model Diffing
  ☆59Updated 10 months ago
• ArthurConmy / Automatic-Circuit-Discovery
  ☆240Updated 11 months ago
• callummcdougall / ARENA_2.0
  Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.
  ☆226Updated last month
• METR / task-standard
  METR Task Standard
  ☆159Updated 7 months ago
• TransluceAI / observatory
  A toolkit for describing model features and intervening on those features to steer behavior.
  ☆201Updated 10 months ago
• redwoodresearch / Easy-Transformer
  ☆122Updated last year
• ApolloResearch / apd
  Attribution-based Parameter Decomposition
  ☆30Updated 3 months ago
• curt-tigges / probity
  ☆17Updated 5 months ago
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆289Updated 9 months ago
• METR / RE-Bench
  ☆99Updated 4 months ago
• EleutherAI / delphi
  Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …
  ☆211Updated last week
• saprmarks / feature-circuits
  ☆186Updated 2 months ago
• redwoodresearch / alignment_faking_public
  ☆76Updated 3 months ago
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆54Updated 4 months ago
• Aaquib111 / edge-attribution-patching
  Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"
  ☆41Updated last year
• amack315 / unsupervised-steering-vectors
  ☆34Updated last year
• Butanium / nnterp
  Unified access to Large Language Model modules using NNsight
  ☆44Updated this week
• neelnanda-io / Crosscoders
  ☆54Updated 10 months ago
• UKGovernmentBEIS / control-arena
  ControlArena is a collection of settings, model organisms and protocols - for running control experiments.
  ☆93Updated this week
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆219Updated 9 months ago
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆124Updated 6 months ago
• jacobdunefsky / transcoder_circuits
  ☆168Updated 10 months ago
• adamkarvonen / SAEBench
  ☆121Updated this week
• ARBORproject / arborproject.github.io
  ☆81Updated 6 months ago
• jbloomAus / SAEDashboard
  ☆68Updated 2 weeks ago
• slavachalnev / SAE-TS
  Improving Steering Vectors by Targeting Sparse Autoencoder Features
  ☆24Updated 10 months ago
• anthropics / toy-models-of-superposition
  Notebooks accompanying Anthropic's "Toy Models of Superposition" paper
  ☆128Updated 3 years ago
• nrimsky / LM-exp
  LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
  ☆97Updated 2 years ago