Alternatives and similar repositories for interp

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

• TomFrederik / unseal
  Mechanistic Interpretability for Transformer Models
  ☆51Updated 3 years ago
• JacobPfau / procgenAISC
  ☆19Updated 2 years ago
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆70Updated 2 months ago
• EleutherAI / elk-generalization
  Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…
  ☆28Updated last year
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆53Updated 2 months ago
• google-deepmind / dangerous-capability-evaluations
  ☆55Updated 9 months ago
• samacqua / LARC
  Language-annotated Abstraction and Reasoning Corpus
  ☆88Updated 2 years ago
• METR / RE-Bench
  ☆92Updated 2 months ago
• koayon / atp_star
  PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)
  ☆18Updated 5 months ago
• noanabeshima / matryoshka-saes
  ☆18Updated 7 months ago
• Sea-Snell / grokking
  unofficial re-implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"
  ☆77Updated 3 years ago
• callummcdougall / sae_visualizer
  ☆28Updated last year
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆122Updated last year
• longtermrisk / openweights
  A python sdk for LLM finetuning and inference on runpod infrastructure
  ☆11Updated last week
• redwoodresearch / alignment_faking_public
  ☆69Updated last month
• aypan17 / machiavelli
  ☆137Updated 8 months ago
• adamkarvonen / SAE_BoardGameEval
  ☆23Updated 5 months ago
• Butanium / nnterp
  A small package implementing some useful wrapping around nnsight
  ☆14Updated this week
• Aaquib111 / edge-attribution-patching
  Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"
  ☆40Updated last year
• nrimsky / InfluenceFunctions
  Implementation of Influence Function approximations for differently sized ML models, using PyTorch
  ☆15Updated last year
• timaeus-research / devinterp
  Tools for studying developmental interpretability in neural networks.
  ☆99Updated 3 weeks ago
• ckkissane / crosscoder-model-diff-replication
  Open source replication of Anthropic's Crosscoders for Model Diffing
  ☆56Updated 8 months ago
• nostalgebraist / transformer-utils
  Utilities for the HuggingFace transformers library
  ☆68Updated 2 years ago
• KoyenaPal / future-lens
  Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State
  ☆18Updated last year
• victorvikram / ConceptARC
  Materials for ConceptARC paper
  ☆96Updated 8 months ago
• likenneth / othello_world
  Emergent world representations: Exploring a sequence model trained on a synthetic task
  ☆182Updated 2 years ago
• FlyingPumba / InterpBench
  A benchmark for mechanistic discovery of circuits in Transformers
  ☆14Updated 7 months ago
• andyljones / boardlaw
  Scaling scaling laws with board games.
  ☆49Updated last year
• thestephencasper / everything-you-need
  we got you bro
  ☆35Updated 11 months ago
• jbloomAus / DecisionTransformerInterpretability
  Interpreting how transformers simulate agents performing RL tasks
  ☆87Updated last year