Alternatives and similar repositories for crosslayer-coding

Users that are interested in crosslayer-coding are comparing it to the libraries listed below

• curt-tigges / probity
  ☆15Updated 4 months ago
• Butanium / nnterp
  Unified access to Large Language Model modules using NNsight
  ☆44Updated last week
• science-of-finetuning / crosscoder_learning
  Modified to support crosscoder training.
  ☆22Updated last month
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆281Updated 8 months ago
• Butanium / tiny-activation-dashboard
  A tiny easily hackable implementation of a feature dashboard.
  ☆12Updated last month
• ARBORproject / arborproject.github.io
  ☆81Updated 6 months ago
• neelnanda-io / Crosscoders
  ☆53Updated 9 months ago
• EleutherAI / delphi
  Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …
  ☆207Updated last week
• tilde-research / activault
  Engine for collecting, uploading, and downloading model activations
  ☆22Updated 4 months ago
• adamkarvonen / SAEBench
  ☆116Updated last month
• amack315 / unsupervised-steering-vectors
  ☆33Updated last year
• ArthurConmy / Automatic-Circuit-Discovery
  ☆238Updated 11 months ago
• saprmarks / dictionary_learning
  ☆335Updated last week
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆54Updated 4 months ago
• tilde-research / sieve
  Applying SAEs for fine-grained control
  ☆23Updated 8 months ago
• saprmarks / feature-circuits
  ☆184Updated last month
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆126Updated last year
• safety-research / safety-tooling
  Inference API for many LLMs and other useful tools for empirical research
  ☆68Updated 2 weeks ago
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆214Updated 8 months ago
• ndif-team / nnsight
  The nnsight package enables interpreting and manipulating the internals of deep learned models.
  ☆638Updated last week
• koayon / atp_star
  PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)
  ☆19Updated 7 months ago
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆76Updated last month
• atticusg / CausalAbstraction
  ☆21Updated 3 weeks ago
• redwoodresearch / Easy-Transformer
  ☆122Updated last year
• ApolloResearch / apd
  Attribution-based Parameter Decomposition
  ☆29Updated 2 months ago
• ckkissane / crosscoder-model-diff-replication
  Open source replication of Anthropic's Crosscoders for Model Diffing
  ☆58Updated 10 months ago
• jacobdunefsky / transcoder_circuits
  ☆163Updated 9 months ago
• ai-safety-foundation / sparse_autoencoder
  Sparse Autoencoder for Mechanistic Interpretability
  ☆260Updated last year
• Aaquib111 / edge-attribution-patching
  Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"
  ☆40Updated last year
• wesg52 / sparse-probing-paper
  Sparse probing paper full code.
  ☆59Updated last year