Alternatives and similar repositories for mlab:

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

• callummcdougall / ARENA_2.0
  Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.
  ☆209Updated 11 months ago
• danielmamay / mlab
  Machine Learning for Alignment Bootcamp (MLAB).
  ☆24Updated 3 years ago
• METR / task-standard
  METR Task Standard
  ☆137Updated 3 weeks ago
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆223Updated last month
• LRudL / evalugator
  (Model-written) LLM evals library
  ☆17Updated last month
• METR / vivaria
  Vivaria is METR's tool for running evaluations and conducting agent elicitation research.
  ☆77Updated this week
• timaeus-research / devinterp
  Tools for studying developmental interpretability in neural networks.
  ☆83Updated this week
• ArthurConmy / Automatic-Circuit-Discovery
  ☆202Updated 3 months ago
• EleutherAI / elk
  Keeping language models honest by directly eliciting knowledge encoded in their activations.
  ☆193Updated this week
• thestephencasper / everything-you-need
  we got you bro
  ☆34Updated 6 months ago
• redwoodresearch / rust_circuit_public
  ☆61Updated last year
• redwoodresearch / interp
  Redwood Research's transformer interpretability tools
  ☆13Updated 2 years ago
• slavachalnev / SAE-TS
  Improving Steering Vectors by Targeting Sparse Autoencoder Features
  ☆14Updated 2 months ago
• METR / public-tasks
  ☆82Updated 3 weeks ago
• TomFrederik / unseal
  Mechanistic Interpretability for Transformer Models
  ☆49Updated 2 years ago
• Cadenza-Labs / sleeper-agents
  ☆10Updated 6 months ago
• EffiSciencesResearch / ML4G
  Machine Learning for Alignment Bootcamp
  ☆25Updated 10 months ago
• callummcdougall / ARENA_3.0
  ☆428Updated this week
• google-deepmind / dangerous-capability-evaluations
  ☆49Updated 4 months ago
• anthropics / toy-models-of-superposition
  Notebooks accompanying Anthropic's "Toy Models of Superposition" paper
  ☆108Updated 2 years ago
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆117Updated last year
• ndif-team / nnsight
  The nnsight package enables interpreting and manipulating the internals of deep learned models.
  ☆469Updated this week
• redwoodresearch / remix_public
  ☆19Updated last year
• alignedai / HappyFaces
  The Happy Faces Benchmark
  ☆14Updated last year
• apartresearch / interpretability-starter
  🧠 Starter templates for doing interpretability research
  ☆65Updated last year
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆177Updated last month
• moirage / alignment-research-dataset
  A dataset of alignment research and code to reproduce it
  ☆73Updated last year
• anthropics / evals
  ☆249Updated 6 months ago
• amack315 / unsupervised-steering-vectors
  ☆28Updated 9 months ago