Alternatives and similar repositories for devinterp:

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

• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆227Updated last month
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆116Updated last year
• callummcdougall / ARENA_2.0
  Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.
  ☆209Updated last year
• ArthurConmy / Automatic-Circuit-Discovery
  ☆203Updated 4 months ago
• TomFrederik / unseal
  Mechanistic Interpretability for Transformer Models
  ☆49Updated 2 years ago
• anthropics / toy-models-of-superposition
  Notebooks accompanying Anthropic's "Toy Models of Superposition" paper
  ☆111Updated 2 years ago
• thestephencasper / everything-you-need
  we got you bro
  ☆34Updated 6 months ago
• jacobdunefsky / transcoder_circuits
  ☆54Updated 2 months ago
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆182Updated 2 months ago
• EleutherAI / delphi
  ☆149Updated this week
• LRudL / evalugator
  (Model-written) LLM evals library
  ☆18Updated 2 months ago
• apartresearch / interpretability-starter
  🧠 Starter templates for doing interpretability research
  ☆65Updated last year
• callummcdougall / sae_visualizer
  ☆25Updated 10 months ago
• amack315 / unsupervised-steering-vectors
  ☆29Updated 9 months ago
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆41Updated 3 months ago
• redwoodresearch / Easy-Transformer
  ☆109Updated 6 months ago
• adamkarvonen / SAEBench
  ☆50Updated last week
• ai-safety-foundation / sparse_autoencoder
  Sparse Autoencoder for Mechanistic Interpretability
  ☆215Updated 6 months ago
• redwoodresearch / rust_circuit_public
  ☆61Updated last year
• saprmarks / dictionary_learning
  ☆235Updated this week
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆87Updated 2 months ago
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆53Updated 2 months ago
• saprmarks / feature-circuits
  ☆140Updated 2 weeks ago
• HoagyC / sparse_coding
  Using sparse coding to find distributed representations used by neural networks.
  ☆213Updated last year
• ndif-team / nnsight
  The nnsight package enables interpreting and manipulating the internals of deep learned models.
  ☆488Updated this week
• alan-cooney / transformer-from-scratch
  Decoder only transformer, built from scratch with PyTorch
  ☆26Updated last year
• neelnanda-io / Crosscoders
  ☆25Updated 2 months ago
• Aaquib111 / edge-attribution-patching
  Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"
  ☆29Updated 8 months ago
• jbloomAus / SAEDashboard
  ☆29Updated this week
• bilal-chughtai / rep-theory-mech-interp
  ☆26Updated last year