dan-gittik / infosec17

Related projects ⓘ

Alternatives and complementary repositories for infosec17

• srush / Autodiff-Puzzles
  ☆388Updated 3 weeks ago
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆196Updated 3 months ago
• alignedai / HappyFaces
  The Happy Faces Benchmark
  ☆14Updated last year
• soniajoseph / ViT-Prisma
  ViT Prisma is a mechanistic interpretability library for Vision Transformers (ViTs).
  ☆174Updated this week
• srush / raspy
  An interactive exploration of Transformer programming.
  ☆245Updated 11 months ago
• jbloomAus / SAELens
  Training Sparse Autoencoders on Language Models
  ☆453Updated this week
• google-deepmind / tracr
  ☆507Updated 9 months ago
• srush / Transformer-Puzzles
  Puzzles for exploring transformers
  ☆323Updated last year
• timaeus-research / devinterp
  Tools for studying developmental interpretability in neural networks.
  ☆75Updated this week
• Mech-Interp / PySvelte
  A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizations
  ☆13Updated 6 months ago
• xl0 / lovely-tensors
  Tensors, for human consumption
  ☆1,111Updated 2 weeks ago
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆108Updated last year
• HoagyC / sparse_coding
  Using sparse coding to find distributed representations used by neural networks.
  ☆181Updated last year
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆158Updated last month
• EleutherAI / concept-erasure
  Erasing concepts from neural representations with provable guarantees
  ☆208Updated 3 weeks ago
• LRudL / evalugator
  (Model-written) LLM evals library
  ☆16Updated 3 months ago
• callummcdougall / ARENA_2.0
  Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.
  ☆197Updated 9 months ago
• collin-burns / discovering_latent_knowledge
  ☆252Updated 8 months ago
• EleutherAI / elk
  Keeping language models honest by directly eliciting knowledge encoded in their activations.
  ☆186Updated last week
• ArthurConmy / Automatic-Circuit-Discovery
  ☆187Updated last month
• inverse-scaling / prize
  A prize for finding tasks that cause large language models to show inverse scaling
  ☆597Updated last year
• Kiv / fancy_einsum
  Einsum with einops style variable names
  ☆15Updated 5 months ago
• craffel / llm-seminar
  Seminar on Large Language Models (COMP790-101 at UNC Chapel Hill, Fall 2022)
  ☆308Updated last year
• ai-safety-foundation / sparse_autoencoder
  Sparse Autoencoder for Mechanistic Interpretability
  ☆188Updated 3 months ago
• anthropics / PySvelte
  A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizations
  ☆172Updated 2 years ago
• google-deepmind / nanodo
  ☆197Updated 3 months ago
• srush / GPTWorld
  A puzzle to learn about prompting
  ☆120Updated last year
• redwoodresearch / Easy-Transformer
  ☆96Updated 3 months ago
• johnmarktaylor91 / torchlens
  Package for extracting and mapping the results of every single tensor operation in a PyTorch model in one line of code.
  ☆479Updated 2 weeks ago
• google-deepmind / neural_networks_chomsky_hierarchy
  Neural Networks and the Chomsky Hierarchy
  ☆187Updated 7 months ago