google-deepmind / tracr

Related projects ⓘ

Alternatives and complementary repositories for tracr

• tech-srl / RASP
  An interpreter for RASP as described in the ICML 2021 paper "Thinking Like Transformers"
  ☆284Updated 2 months ago
• AlignmentResearch / tuned-lens
  Tools for understanding how transformer predictions are built layer-by-layer
  ☆430Updated 5 months ago
• srush / raspy
  An interactive exploration of Transformer programming.
  ☆246Updated last year
• google-deepmind / neural_networks_chomsky_hierarchy
  Neural Networks and the Chomsky Hierarchy
  ☆187Updated 7 months ago
• EleutherAI / elk
  Keeping language models honest by directly eliciting knowledge encoded in their activations.
  ☆186Updated this week
• collin-burns / discovering_latent_knowledge
  ☆253Updated 8 months ago
• likenneth / othello_world
  Emergent world representations: Exploring a sequence model trained on a synthetic task
  ☆169Updated last year
• HazyResearch / H3
  Language Modeling with the H3 State Space Model
  ☆513Updated last year
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆198Updated 4 months ago
• stanford-crfm / levanter
  Legible, Scalable, Reproducible Foundation Models with Named Tensors and Jax
  ☆516Updated this week
• srush / Transformer-Puzzles
  Puzzles for exploring transformers
  ☆325Updated last year
• jxbz / agd
  Automatic gradient descent
  ☆206Updated last year
• google-research / cascades
  Python library which enables complex compositions of language models such as scratchpads, chain of thought, tool use, selection-inference…
  ☆196Updated 5 months ago
• EleutherAI / concept-erasure
  Erasing concepts from neural representations with provable guarantees
  ☆209Updated last week
• sanjeevanahilan / nanoChatGPT
  A crude RLHF layer on top of nanoGPT with Gumbel-Softmax trick
  ☆287Updated 11 months ago
• anthropics / toy-models-of-superposition
  Notebooks accompanying Anthropic's "Toy Models of Superposition" paper
  ☆97Updated 2 years ago
• mcleish7 / arithmetic
  Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)
  ☆178Updated 5 months ago
• lucidrains / memorizing-transformers-pytorch
  Implementation of Memorizing Transformers (ICLR 2022), attention net augmented with indexing and retrieval of memories using approximate …
  ☆624Updated last year
• callummcdougall / ARENA_2.0
  Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.
  ☆200Updated 9 months ago
• soniajoseph / ViT-Prisma
  ViT Prisma is a mechanistic interpretability library for Vision Transformers (ViTs).
  ☆179Updated this week
• ArthurConmy / Automatic-Circuit-Discovery
  ☆188Updated last month
• r-three / git-theta
  git extension for {collaborative, communal, continual} model development
  ☆205Updated this week
• google-deepmind / nanodo
  ☆197Updated 4 months ago
• google-research / meliad
  ☆251Updated 2 years ago
• jbloomAus / SAELens
  Training Sparse Autoencoders on Language Models
  ☆469Updated this week
• samuela / git-re-basin
  Code release for "Git Re-Basin: Merging Models modulo Permutation Symmetries"
  ☆471Updated last year
• anthropics / evals
  ☆239Updated 4 months ago
• justinchiu / openlogprobs
  Extract full next-token probabilities via language model APIs
  ☆229Updated 8 months ago
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆157Updated last month