anthropics / PySvelte

Related projects: ⓘ

• TomFrederik / unseal
  Mechanistic Interpretability for Transformer Models
  ☆48Updated 2 years ago
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆175Updated 2 months ago
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆99Updated 10 months ago
• AlignmentResearch / tuned-lens
  Tools for understanding how transformer predictions are built layer-by-layer
  ☆408Updated 3 months ago
• callummcdougall / sae_visualizer
  ☆24Updated 5 months ago
• ArthurConmy / Automatic-Circuit-Discovery
  ☆174Updated 4 months ago
• apartresearch / interpretability-starter
  🧠 Starter templates for doing interpretability research
  ☆59Updated last year
• anthropics / toy-models-of-superposition
  Notebooks accompanying Anthropic's "Toy Models of Superposition" paper
  ☆88Updated 2 years ago
• collin-burns / discovering_latent_knowledge
  ☆246Updated 6 months ago
• timaeus-research / devinterp
  Tools for studying developmental interpretability in neural networks.
  ☆69Updated this week
• EleutherAI / elk
  Keeping language models honest by directly eliciting knowledge encoded in their activations.
  ☆182Updated this week
• likenneth / othello_world
  Emergent world representations: Exploring a sequence model trained on a synthetic task
  ☆165Updated last year
• saprmarks / dictionary_learning
  ☆110Updated 3 weeks ago
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆133Updated last month
• callummcdougall / ARENA_2.0
  Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.
  ☆185Updated 7 months ago
• saprmarks / feature-circuits
  ☆75Updated this week
• jacobdunefsky / transcoder_circuits
  ☆33Updated 3 months ago
• alignedai / HappyFaces
  The Happy Faces Benchmark
  ☆14Updated last year
• samacqua / LARC
  Language-annotated Abstraction and Reasoning Corpus
  ☆76Updated last year
• google-deepmind / neural_networks_chomsky_hierarchy
  Neural Networks and the Chomsky Hierarchy
  ☆183Updated 5 months ago
• redwoodresearch / Easy-Transformer
  ☆91Updated last month
• EleutherAI / concept-erasure
  Erasing concepts from neural representations with provable guarantees
  ☆202Updated 3 months ago
• ndif-team / nnsight
  The nnsight package enables interpreting and manipulating the internals of deep learned models.
  ☆356Updated this week
• EleutherAI / sae-auto-interp
  ☆54Updated last week
• google-deepmind / nanodo
  ☆180Updated 2 months ago
• HoagyC / sparse_coding
  Using sparse coding to find distributed representations used by neural networks.
  ☆162Updated 10 months ago
• michaelhodel / re-arc
  Reverse Engineering the Abstraction and Reasoning Corpus
  ☆130Updated last month
• srush / raspy
  An interactive exploration of Transformer programming.
  ☆243Updated 10 months ago
• PAIR-code / interpretability
  PAIR.withgoogle.com and friend's work on interpretability methods
  ☆138Updated last week
• soniajoseph / ViT-Prisma
  ViT Prisma is a mechanistic interpretability library for Vision Transformers (ViTs).
  ☆161Updated this week