Alternatives and similar repositories for transformer-from-scratch

Users that are interested in transformer-from-scratch are comparing it to the libraries listed below

• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆297Updated 10 months ago
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆224Updated 10 months ago
• ArthurConmy / Automatic-Circuit-Discovery
  ☆252Updated 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 …
  ☆221Updated last week
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆131Updated 2 years ago
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆127Updated 8 months ago
• jacobdunefsky / transcoder_circuits
  ☆183Updated 11 months ago
• EleutherAI / sparsify
  Sparsify transformers with SAEs and transcoders
  ☆652Updated this week
• saprmarks / dictionary_learning
  ☆356Updated 2 months ago
• ndif-team / nnsight
  The nnsight package enables interpreting and manipulating the internals of deep learned models.
  ☆692Updated last week
• ai-safety-foundation / sparse_autoencoder
  Sparse Autoencoder for Mechanistic Interpretability
  ☆283Updated last year
• neelnanda-io / Crosscoders
  ☆55Updated 11 months ago
• callummcdougall / ARENA_2.0
  Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.
  ☆231Updated 2 months ago
• ckkissane / crosscoder-model-diff-replication
  Open source replication of Anthropic's Crosscoders for Model Diffing
  ☆59Updated last year
• saprmarks / feature-circuits
  ☆192Updated 3 weeks ago
• ApolloResearch / apd
  Attribution-based Parameter Decomposition
  ☆31Updated 4 months ago
• amack315 / unsupervised-steering-vectors
  ☆36Updated last year
• timaeus-research / devinterp
  Tools for studying developmental interpretability in neural networks.
  ☆114Updated 4 months ago
• adamkarvonen / SAEBench
  ☆133Updated 3 weeks ago
• HoagyC / sparse_coding
  Using sparse coding to find distributed representations used by neural networks.
  ☆281Updated last year
• goodfire-ai / r1-interpretability
  Open source interpretability artefacts for R1.
  ☆163Updated 6 months ago
• redwoodresearch / Easy-Transformer
  ☆128Updated last year
• TransluceAI / observatory
  A toolkit for describing model features and intervening on those features to steer behavior.
  ☆211Updated last year
• TransluceAI / docent
  ☆59Updated last month
• curt-tigges / probity
  ☆19Updated 6 months ago
• ARBORproject / arborproject.github.io
  ☆81Updated 8 months ago
• anthropics / toy-models-of-superposition
  Notebooks accompanying Anthropic's "Toy Models of Superposition" paper
  ☆129Updated 3 years ago
• science-of-finetuning / crosscoder_learning
  Modified to support crosscoder training.
  ☆24Updated last month
• Aaquib111 / edge-attribution-patching
  Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"
  ☆42Updated last year
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆79Updated 3 months ago