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
  ☆154Updated 5 months ago
• UKGovernmentBEIS / inspect_evals
  Collection of evals for Inspect AI
  ☆178Updated this week
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆262Updated 7 months ago
• safety-research / safety-tooling
  Inference API for many LLMs and other useful tools for empirical research
  ☆52Updated this week
• ArthurConmy / Automatic-Circuit-Discovery
  ☆231Updated 9 months ago
• redwoodresearch / alignment_faking_public
  ☆69Updated last month
• EleutherAI / delphi
  Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …
  ☆193Updated this week
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆206Updated 7 months ago
• saprmarks / feature-circuits
  ☆182Updated 3 months ago
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆115Updated 4 months ago
• ckkissane / crosscoder-model-diff-replication
  Open source replication of Anthropic's Crosscoders for Model Diffing
  ☆57Updated 8 months ago
• anthropics / sleeper-agents-paper
  Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".
  ☆109Updated last year
• google-deepmind / dangerous-capability-evaluations
  ☆55Updated 9 months ago
• google-deepmind / mishax
  ☆134Updated 3 months ago
• ai-safety-foundation / sparse_autoencoder
  Sparse Autoencoder for Mechanistic Interpretability
  ☆255Updated 11 months ago
• METR / vivaria
  Vivaria is METR's tool for running evaluations and conducting agent elicitation research.
  ☆99Updated 3 weeks ago
• callummcdougall / ARENA_2.0
  Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.
  ☆216Updated last year
• amack315 / unsupervised-steering-vectors
  ☆32Updated last year
• aypan17 / machiavelli
  ☆137Updated 8 months ago
• timaeus-research / devinterp
  Tools for studying developmental interpretability in neural networks.
  ☆99Updated 3 weeks ago
• emergent-misalignment / emergent-misalignment
  ☆171Updated 4 months ago
• EleutherAI / elk
  Keeping language models honest by directly eliciting knowledge encoded in their activations.
  ☆207Updated this week
• redwoodresearch / Easy-Transformer
  ☆121Updated 11 months ago
• thestephencasper / everything-you-need
  we got you bro
  ☆35Updated 11 months ago
• nrimsky / LM-exp
  LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
  ☆95Updated last year
• TransluceAI / observatory
  A toolkit for describing model features and intervening on those features to steer behavior.
  ☆193Updated 8 months ago
• EleutherAI / elk-generalization
  Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…
  ☆28Updated last year
• nrimsky / CAA
  Steering Llama 2 with Contrastive Activation Addition
  ☆164Updated last year
• apartresearch / interpretability-starter
  🧠 Starter templates for doing interpretability research
  ☆72Updated 2 years ago
• anthropics / toy-models-of-superposition
  Notebooks accompanying Anthropic's "Toy Models of Superposition" paper
  ☆127Updated 2 years ago