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
  ☆159Updated 7 months ago
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆289Updated 9 months ago
• ArthurConmy / Automatic-Circuit-Discovery
  ☆240Updated 11 months ago
• safety-research / safety-tooling
  Inference API for many LLMs and other useful tools for empirical research
  ☆68Updated last week
• UKGovernmentBEIS / inspect_evals
  Collection of evals for Inspect AI
  ☆230Updated last week
• LRudL / evalugator
  (Model-written) LLM evals library
  ☆18Updated 9 months ago
• anthropics / toy-models-of-superposition
  Notebooks accompanying Anthropic's "Toy Models of Superposition" paper
  ☆128Updated 3 years 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
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆219Updated 9 months ago
• TransluceAI / observatory
  A toolkit for describing model features and intervening on those features to steer behavior.
  ☆201Updated 10 months ago
• ai-safety-foundation / sparse_autoencoder
  Sparse Autoencoder for Mechanistic Interpretability
  ☆265Updated last year
• timaeus-research / devinterp
  Tools for studying developmental interpretability in neural networks.
  ☆103Updated 2 months ago
• saprmarks / feature-circuits
  ☆186Updated 2 months ago
• redwoodresearch / alignment_faking_public
  ☆76Updated 3 months ago
• METR / vivaria
  Vivaria is METR's tool for running evaluations and conducting agent elicitation research.
  ☆111Updated this week
• ndif-team / nnsight
  The nnsight package enables interpreting and manipulating the internals of deep learned models.
  ☆661Updated last week
• 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
• Butanium / nnterp
  Unified access to Large Language Model modules using NNsight
  ☆44Updated this week
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆124Updated 6 months ago
• METR / public-tasks
  ☆103Updated 6 months ago
• adamkarvonen / SAEBench
  ☆121Updated this week
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆127Updated last year
• saprmarks / dictionary_learning
  ☆345Updated last month
• google-deepmind / dangerous-capability-evaluations
  ☆57Updated last month
• EleutherAI / elk
  Keeping language models honest by directly eliciting knowledge encoded in their activations.
  ☆209Updated this week
• amack315 / unsupervised-steering-vectors
  ☆34Updated last year
• redwoodresearch / mlab
  Machine Learning for Alignment Bootcamp
  ☆78Updated 3 years ago
• redwoodresearch / Easy-Transformer
  ☆122Updated last year
• anthropics / evals
  ☆298Updated last year
• anthropics / sleeper-agents-paper
  Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".
  ☆115Updated last year