alan-cooney / transformer-from-scratch

Related projects ⓘ

Alternatives and complementary repositories for transformer-from-scratch

• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆157Updated last month
• HoagyC / sparse_coding
  Using sparse coding to find distributed representations used by neural networks.
  ☆185Updated last year
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆65Updated last month
• jacobdunefsky / transcoder_circuits
  ☆44Updated this week
• saprmarks / dictionary_learning
  ☆145Updated 3 weeks ago
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆200Updated 4 months ago
• ArthurConmy / Automatic-Circuit-Discovery
  ☆188Updated last month
• saprmarks / feature-circuits
  ☆105Updated last month
• EleutherAI / sae-auto-interp
  ☆107Updated this week
• redwoodresearch / Easy-Transformer
  ☆98Updated 3 months ago
• nrimsky / CAA
  Steering Llama 2 with Contrastive Activation Addition
  ☆98Updated 5 months ago
• ai-safety-foundation / sparse_autoencoder
  Sparse Autoencoder for Mechanistic Interpretability
  ☆188Updated 4 months ago
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆108Updated last year
• EleutherAI / sae
  Sparse autoencoders
  ☆344Updated last week
• Cadenza-Labs / sleeper-agents
  ☆10Updated 4 months ago
• ndif-team / nnsight
  The nnsight package enables interpreting and manipulating the internals of deep learned models.
  ☆406Updated this week
• jbloomAus / SAELens
  Training Sparse Autoencoders on Language Models
  ☆469Updated this week
• OpenMOSS / Language-Model-SAEs
  For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.
  ☆48Updated this week
• timaeus-research / devinterp
  Tools for studying developmental interpretability in neural networks.
  ☆77Updated last week
• ruizheliUOA / Awesome-Interpretability-in-Large-Language-Models
  This repository collects all relevant resources about interpretability in LLMs
  ☆289Updated 3 weeks ago
• mcleish7 / arithmetic
  Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)
  ☆179Updated 5 months ago
• nrimsky / LM-exp
  LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
  ☆78Updated last year
• LoryPack / LLM-LieDetector
  Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"
  ☆62Updated 5 months ago
• wesg52 / sparse-probing-paper
  Sparse probing paper full code.
  ☆51Updated 11 months ago
• amack315 / unsupervised-steering-vectors
  ☆24Updated 6 months ago
• andyrdt / refusal_direction
  Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".
  ☆123Updated last month
• HazyResearch / zoology
  Understand and test language model architectures on synthetic tasks.
  ☆162Updated 6 months ago
• collin-burns / discovering_latent_knowledge
  ☆253Updated 8 months ago
• openai / sparse_autoencoder
  ☆328Updated 4 months ago
• 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