EffiSciencesResearch / ML4G

Related projects: ⓘ

• timaeus-research / devinterp
  Tools for studying developmental interpretability in neural networks.
  ☆69Updated this week
• callummcdougall / ARENA_2.0
  Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.
  ☆185Updated 7 months ago
• redwoodresearch / mlab
  Machine Learning for Alignment Bootcamp
  ☆62Updated 2 years ago
• apartresearch / interpretability-starter
  🧠 Starter templates for doing interpretability research
  ☆59Updated last year
• callummcdougall / sae_visualizer
  ☆24Updated 5 months ago
• danielmamay / mlab
  Machine Learning for Alignment Bootcamp (MLAB).
  ☆22Updated 2 years ago
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆175Updated 2 months ago
• redwoodresearch / remix_public
  ☆18Updated last year
• EleutherAI / elk
  Keeping language models honest by directly eliciting knowledge encoded in their activations.
  ☆182Updated this week
• moirage / alignment-research-dataset
  A dataset of alignment research and code to reproduce it
  ☆68Updated last year
• TomFrederik / unseal
  Mechanistic Interpretability for Transformer Models
  ☆48Updated 2 years ago
• ArthurConmy / Automatic-Circuit-Discovery
  ☆174Updated 4 months ago
• EleutherAI / concept-erasure
  Erasing concepts from neural representations with provable guarantees
  ☆202Updated 3 months ago
• LRudL / evalugator
  (Model-written) LLM evals library
  ☆14Updated last month
• alignedai / HappyFaces
  The Happy Faces Benchmark
  ☆14Updated last year
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆99Updated 10 months ago
• thestephencasper / everything-you-need
  we got you bro
  ☆32Updated last month
• Mech-Interp / PySvelte
  A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizations
  ☆13Updated 5 months ago
• google-deepmind / dangerous-capability-evaluations
  ☆39Updated 2 months ago
• google-deepmind / mishax
  ☆91Updated last month
• METR / public-tasks
  ☆58Updated last week
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆133Updated last month
• anthropics / toy-models-of-superposition
  Notebooks accompanying Anthropic's "Toy Models of Superposition" paper
  ☆88Updated 2 years ago
• jessicarumbelow / Backwards
  ☆72Updated 2 months ago
• neoneye / arc-notes
  My writings about ARC (Abstraction and Reasoning Corpus)
  ☆55Updated 3 weeks ago
• srush / GPTWorld
  A puzzle to learn about prompting
  ☆106Updated last year
• METR / task-standard
  METR Task Standard
  ☆111Updated last week
• collin-burns / discovering_latent_knowledge
  ☆246Updated 6 months ago
• anthropics / evals
  ☆229Updated 2 months ago
• neoneye / ARC-Interactive-History-Dataset
  The history files when recording human interaction while solving ARC tasks
  ☆91Updated this week