alan-cooney / transformer-from-scratch

Related projects: ⓘ

• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆133Updated last month
• HoagyC / sparse_coding
  Using sparse coding to find distributed representations used by neural networks.
  ☆162Updated 10 months ago
• saprmarks / dictionary_learning
  ☆110Updated 3 weeks ago
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆175Updated 2 months ago
• ai-safety-foundation / sparse_autoencoder
  Sparse Autoencoder for Mechanistic Interpretability
  ☆173Updated 2 months ago
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆52Updated 2 months ago
• ArthurConmy / Automatic-Circuit-Discovery
  ☆174Updated 4 months ago
• jbloomAus / SAELens
  Training Sparse Autoencoders on Language Models
  ☆367Updated this week
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆99Updated 10 months ago
• EleutherAI / sae
  Sparse autoencoders
  ☆297Updated last week
• saprmarks / feature-circuits
  ☆75Updated this week
• redwoodresearch / Easy-Transformer
  ☆91Updated last month
• nrimsky / CAA
  Steering Llama 2 with Contrastive Activation Addition
  ☆83Updated 3 months ago
• EleutherAI / sae-auto-interp
  ☆54Updated last week
• ndif-team / nnsight
  The nnsight package enables interpreting and manipulating the internals of deep learned models.
  ☆356Updated this week
• jacobdunefsky / transcoder_circuits
  ☆33Updated 3 months ago
• ruizheliUOA / Awesome-Interpretability-in-Large-Language-Models
  This repository collects all relevant resources about interpretability in LLMs
  ☆230Updated last week
• Cadenza-Labs / sleeper-agents
  ☆10Updated 2 months ago
• andyrdt / refusal_direction
  Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".
  ☆76Updated 3 weeks ago
• timaeus-research / devinterp
  Tools for studying developmental interpretability in neural networks.
  ☆69Updated this week
• openai / sparse_autoencoder
  ☆267Updated 2 months ago
• likenneth / othello_world
  Emergent world representations: Exploring a sequence model trained on a synthetic task
  ☆165Updated last year
• HazyResearch / zoology
  Understand and test language model architectures on synthetic tasks.
  ☆156Updated 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.
  ☆185Updated 7 months ago
• collin-burns / discovering_latent_knowledge
  ☆246Updated 6 months ago
• GraySwanAI / circuit-breakers
  Improving Alignment and Robustness with Circuit Breakers
  ☆124Updated 2 months ago
• nrimsky / LM-exp
  LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
  ☆73Updated last year
• callummcdougall / sae_visualizer
  ☆24Updated 5 months ago
• callummcdougall / ARENA_3.0
  ☆274Updated this week
• JoshEngels / MultiDimensionalFeatures
  Code for reproducing our paper "Not All Language Model Features Are Linear"
  ☆57Updated last week