Alternatives and similar repositories for interlab

Users that are interested in interlab are comparing it to the libraries listed below

• moirage / alignment-research-dataset
  A dataset of alignment research and code to reproduce it
  ☆77Updated 2 years ago
• mukobi / welfare-diplomacy
  General-Sum variant of the game Diplomacy for evaluating AIs.
  ☆30Updated last year
• METR / task-standard
  METR Task Standard
  ☆160Updated 7 months ago
• EleutherAI / elk
  Keeping language models honest by directly eliciting knowledge encoded in their activations.
  ☆209Updated this week
• timaeus-research / devinterp
  Tools for studying developmental interpretability in neural networks.
  ☆103Updated 3 months ago
• jprivera44 / EscalAItion
  Repo for the paper on Escalation Risks of AI systems
  ☆44Updated last year
• TomFrederik / unseal
  Mechanistic Interpretability for Transformer Models
  ☆51Updated 3 years ago
• aypan17 / machiavelli
  ☆138Updated 2 months ago
• anthropics / evals
  ☆300Updated last year
• METR / public-tasks
  ☆103Updated this week
• redwoodresearch / mlab
  Machine Learning for Alignment Bootcamp
  ☆78Updated 3 years ago
• google-research / cascades
  Python library which enables complex compositions of language models such as scratchpads, chain of thought, tool use, selection-inference…
  ☆211Updated 3 months ago
• METR / vivaria
  Vivaria is METR's tool for running evaluations and conducting agent elicitation research.
  ☆111Updated this week
• oughtinc / primer
  Factored Cognition Primer: How to write compositional language model programs
  ☆49Updated 2 years ago
• MinhxLe / subliminal-learning
  ☆97Updated last month
• UKGovernmentBEIS / control-arena
  ControlArena is a collection of settings, model organisms and protocols - for running control experiments.
  ☆94Updated this week
• jbloomAus / DecisionTransformerInterpretability
  Interpreting how transformers simulate agents performing RL tasks
  ☆88Updated last year
• google-deepmind / dangerous-capability-evaluations
  ☆57Updated this week
• StampyAI / stampy-chat
  Conversational chatbot to answer questions about AI Safety & Alignment based on information retrieved from the Alignment Research Dataset
  ☆15Updated this week
• poking-agents / modular-public
  ☆26Updated 3 months ago
• oughtinc / patchwork
  Command-line recursive question-answering with immutable contexts and explicit data store
  ☆26Updated 7 years ago
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆289Updated 9 months ago
• safety-research / safety-tooling
  Inference API for many LLMs and other useful tools for empirical research
  ☆71Updated last week
• safety-research / safety-examples
  ☆20Updated 3 months ago
• KihoPark / LLM_Categorical_Hierarchical_Representations
  ☆108Updated 7 months ago
• mishajw / repeng
  Experiments with representation engineering
  ☆12Updated last year
• rgreenblatt / arc_draw_more_samples_pub
  Draw more samples
  ☆193Updated last year
• redwoodresearch / interp
  Redwood Research's transformer interpretability tools
  ☆14Updated 3 years ago
• apartresearch / Neuron2Graph
  Tools for exploring Transformer neuron behaviour, including input pruning and diversification.
  ☆20Updated last year
• benlipkin / probsem
  Probabilistic LLM evaluations. [CogSci2023; ACL2023]
  ☆73Updated last year