Alternatives and similar repositories for guarantees-based-mechanistic-interpretability

Users that are interested in guarantees-based-mechanistic-interpretability are comparing it to the libraries listed below

• Butanium / nnterp
  A small package implementing some useful wrapping around nnsight
  ☆13Updated 3 weeks ago
• koayon / atp_star
  PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)
  ☆18Updated 5 months ago
• timaeus-research / devinterp
  Tools for studying developmental interpretability in neural networks.
  ☆94Updated 5 months ago
• LRudL / evalugator
  (Model-written) LLM evals library
  ☆18Updated 6 months ago
• amack315 / unsupervised-steering-vectors
  ☆31Updated last year
• ApolloResearch / apd
  Attribution-based Parameter Decomposition
  ☆25Updated 2 weeks ago
• gpoesia / minimo
  Learning Formal Mathematics from Intrinsic Motivation
  ☆30Updated 3 months ago
• harmonic-ai / datasets
  Harmonic Datasets
  ☆40Updated 11 months ago
• redwoodresearch / interp
  Redwood Research's transformer interpretability tools
  ☆15Updated 3 years 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…
  ☆27Updated last year
• Mech-Interp / PySvelte
  A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizations
  ☆14Updated last year
• JoshEngels / MultiDimensionalFeatures
  Code for reproducing our paper "Not All Language Model Features Are Linear"
  ☆75Updated 6 months ago
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆52Updated last month
• yeahrmek / pylean
  Python wrapper for lean-gym
  ☆12Updated 2 years ago
• gpoesia / peano
  An environment for learning formal mathematical reasoning from scratch
  ☆70Updated 10 months ago
• tilde-research / sieve
  Applying SAEs for fine-grained control
  ☆18Updated 6 months ago
• longtermrisk / openweights
  A python sdk for LLM finetuning and inference on runpod infrastructure
  ☆11Updated last week
• ejnnr / cupbearer
  A library for mechanistic anomaly detection
  ☆22Updated 5 months ago
• redwoodresearch / alignment_faking_public
  ☆65Updated last month
• google-deepmind / debate
  Formalizing stochastic doubly-efficient debate
  ☆107Updated 8 months ago
• google-deepmind / mishax
  ☆134Updated 2 months ago
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆67Updated 2 months ago
• jbloomAus / SAEDashboard
  ☆57Updated 2 weeks ago
• curt-tigges / probity
  ☆13Updated 2 months ago
• Aaquib111 / edge-attribution-patching
  Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"
  ☆35Updated last year
• slavachalnev / SAE-TS
  Improving Steering Vectors by Targeting Sparse Autoencoder Features
  ☆20Updated 7 months ago
• albertqjiang / Portal-to-ISAbelle
  https://albertqjiang.github.io/Portal-to-ISAbelle/
  ☆56Updated last year
• noanabeshima / matryoshka-saes
  ☆17Updated 6 months ago
• neelnanda-io / Crosscoders
  ☆44Updated 7 months ago
• redwoodresearch / rust_circuit_public
  ☆63Updated 2 years ago