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
  ☆20Updated 8 months ago
• science-of-finetuning / crosscoder_learning
  Modified to support crosscoder training.
  ☆25Updated 3 months ago
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆306Updated last year
• ARBORproject / arborproject.github.io
  ☆83Updated 10 months ago
• neelnanda-io / Crosscoders
  ☆58Updated last year
• Butanium / nnterp
  Unified access to Large Language Model modules using NNsight
  ☆71Updated last week
• ArthurConmy / Automatic-Circuit-Discovery
  ☆262Updated last year
• EleutherAI / delphi
  Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …
  ☆234Updated 2 weeks ago
• saprmarks / feature-circuits
  ☆200Updated 2 months ago
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆236Updated last year
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆132Updated 2 years ago
• tilde-research / activault
  Engine for collecting, uploading, and downloading model activations
  ☆24Updated 9 months ago
• science-of-finetuning / diffing-toolkit
  A toolkit that provides a range of model diffing techniques including a UI to visualize them interactively.
  ☆49Updated this week
• amack315 / unsupervised-steering-vectors
  ☆36Updated last year
• adamkarvonen / SAEBench
  ☆140Updated last week
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆56Updated 8 months ago
• goodfire-ai / causalab
  ☆27Updated 3 weeks ago
• ckkissane / crosscoder-model-diff-replication
  Open source replication of Anthropic's Crosscoders for Model Diffing
  ☆63Updated last year
• ApolloResearch / apd
  Attribution-based Parameter Decomposition
  ☆33Updated 6 months ago
• Aaquib111 / edge-attribution-patching
  Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"
  ☆44Updated last year
• TransluceAI / docent
  ☆75Updated 3 weeks ago
• oli-clive-griffin / crosscode
  A library for training crosscoders
  ☆13Updated 7 months ago
• jacobdunefsky / transcoder_circuits
  ☆193Updated last year
• saprmarks / dictionary_learning
  ☆380Updated 4 months ago
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆84Updated last week
• Butanium / tiny-activation-dashboard
  A tiny easily hackable implementation of a feature dashboard.
  ☆15Updated 2 months ago
• ndif-team / nnsight
  The nnsight package enables interpreting and manipulating the internals of deep learned models.
  ☆747Updated last week
• ai-safety-foundation / sparse_autoencoder
  Sparse Autoencoder for Mechanistic Interpretability
  ☆285Updated last year
• jacobdunefsky / llm-steering-opt
  Tools for optimizing steering vectors in LLMs.
  ☆17Updated 8 months ago
• alan-cooney / transformer-from-scratch
  Decoder only transformer, built from scratch with PyTorch
  ☆32Updated 2 years ago