Alternatives and similar repositories for control-arena

Users that are interested in control-arena are comparing it to the libraries listed below

• METR / task-standard
  METR Task Standard
  ☆168Updated 10 months ago
• safety-research / safety-tooling
  Inference API for many LLMs and other useful tools for empirical research
  ☆84Updated this week
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆302Updated 11 months ago
• UKGovernmentBEIS / inspect_evals
  Collection of evals for Inspect AI
  ☆297Updated last week
• ArthurConmy / Automatic-Circuit-Discovery
  ☆259Updated last year
• redwoodresearch / alignment_faking_public
  ☆81Updated 2 months ago
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆232Updated 11 months ago
• ai-safety-foundation / sparse_autoencoder
  Sparse Autoencoder for Mechanistic Interpretability
  ☆285Updated last year
• timaeus-research / devinterp
  Tools for studying developmental interpretability in neural networks.
  ☆117Updated 5 months ago
• TransluceAI / observatory
  A toolkit for describing model features and intervening on those features to steer behavior.
  ☆220Updated last year
• TransluceAI / docent
  ☆66Updated 2 months ago
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆130Updated 9 months ago
• callummcdougall / ARENA_2.0
  Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.
  ☆233Updated 4 months ago
• GraySwanAI / circuit-breakers
  Improving Alignment and Robustness with Circuit Breakers
  ☆248Updated last year
• saprmarks / feature-circuits
  ☆196Updated last month
• safety-research / safety-examples
  ☆20Updated last month
• EleutherAI / elk
  Keeping language models honest by directly eliciting knowledge encoded in their activations.
  ☆215Updated this week
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆132Updated 2 years ago
• METR / vivaria
  Vivaria is METR's tool for running evaluations and conducting agent elicitation research.
  ☆121Updated last month
• ndif-team / nnsight
  The nnsight package enables interpreting and manipulating the internals of deep learned models.
  ☆716Updated last week
• anthropics / sleeper-agents-paper
  Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".
  ☆122Updated last year
• Butanium / nnterp
  Unified access to Large Language Model modules using NNsight
  ☆68Updated 3 weeks 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 …
  ☆231Updated last week
• google-deepmind / dangerous-capability-evaluations
  ☆62Updated 2 months ago
• jacobdunefsky / transcoder_circuits
  ☆191Updated last year
• nrimsky / LM-exp
  LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
  ☆100Updated 2 years ago
• anthropics / toy-models-of-superposition
  Notebooks accompanying Anthropic's "Toy Models of Superposition" paper
  ☆130Updated 3 years ago
• anthropics / evals
  ☆315Updated last year
• adamkarvonen / SAEBench
  ☆136Updated 3 weeks ago
• HoagyC / sparse_coding
  Using sparse coding to find distributed representations used by neural networks.
  ☆287Updated 2 years ago