Alternatives and similar repositories for public-tasks

Users that are interested in public-tasks are comparing it to the libraries listed below

• METR / task-standard
  METR Task Standard
  ☆167Updated 9 months ago
• METR / vivaria
  Vivaria is METR's tool for running evaluations and conducting agent elicitation research.
  ☆120Updated this week
• emergent-misalignment / emergent-misalignment
  ☆226Updated 2 weeks ago
• UKGovernmentBEIS / control-arena
  ControlArena is a collection of settings, model organisms and protocols - for running control experiments.
  ☆127Updated last week
• METR / RE-Bench
  ☆117Updated last month
• goodfire-ai / r1-interpretability
  Open source interpretability artefacts for R1.
  ☆163Updated 6 months ago
• google-deepmind / mishax
  ☆143Updated 2 months ago
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆299Updated 10 months ago
• TransluceAI / observatory
  A toolkit for describing model features and intervening on those features to steer behavior.
  ☆212Updated last year
• google-deepmind / dangerous-capability-evaluations
  ☆62Updated last month
• poking-agents / modular-public
  ☆32Updated 5 months ago
• rgreenblatt / arc_draw_more_samples_pub
  Draw more samples
  ☆195Updated last year
• anthropics / sleeper-agents-paper
  Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".
  ☆121Updated last year
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆226Updated 11 months ago
• anthropics / evals
  ☆307Updated last year
• timaeus-research / devinterp
  Tools for studying developmental interpretability in neural networks.
  ☆114Updated 4 months ago
• callummcdougall / sae_visualizer
  ☆29Updated last year
• aypan17 / machiavelli
  ☆139Updated 3 months ago
• safety-research / safety-tooling
  Inference API for many LLMs and other useful tools for empirical research
  ☆79Updated last week
• EleutherAI / elk
  Keeping language models honest by directly eliciting knowledge encoded in their activations.
  ☆212Updated last week
• anthropics / toy-models-of-superposition
  Notebooks accompanying Anthropic's "Toy Models of Superposition" paper
  ☆130Updated 3 years ago
• amack315 / unsupervised-steering-vectors
  ☆36Updated last year
• goodfire-ai / scribe
  ☆53Updated last month
• AsaCooperStickland / situational-awareness-evals
  Measuring the situational awareness of language models
  ☆39Updated last year
• UKGovernmentBEIS / inspect_evals
  Collection of evals for Inspect AI
  ☆284Updated this week
• TransluceAI / docent
  ☆61Updated last month
• callummcdougall / ARENA_2.0
  Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.
  ☆231Updated 3 months ago
• anthropics / sycophancy-to-subterfuge-paper
  ☆25Updated last year
• justinchiu / openlogprobs
  Extract full next-token probabilities via language model APIs
  ☆247Updated last year
• MinhxLe / subliminal-learning
  ☆104Updated 3 months ago