TransformerLensOrg / TransformerLens

Related projects ⓘ

Alternatives and complementary repositories for TransformerLens

• jbloomAus / SAELens
  Training Sparse Autoencoders on Language Models
  ☆481Updated this week
• ndif-team / nnsight
  The nnsight package enables interpreting and manipulating the internals of deep learned models.
  ☆406Updated this week
• stanfordnlp / pyvene
  Stanford NLP Python Library for Understanding and Improving PyTorch Models via Interventions
  ☆649Updated 2 weeks ago
• callummcdougall / ARENA_3.0
  ☆354Updated this week
• andyzoujm / representation-engineering
  Representation Engineering: A Top-Down Approach to AI Transparency
  ☆730Updated 3 months ago
• EleutherAI / sae
  Sparse autoencoders
  ☆345Updated this week
• 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
• srush / awesome-o1
  A bibliography and survey of the papers surrounding o1
  ☆795Updated last week
• AlignmentResearch / tuned-lens
  Tools for understanding how transformer predictions are built layer-by-layer
  ☆432Updated 5 months ago
• openai / sparse_autoencoder
  ☆331Updated 4 months ago
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆200Updated 4 months ago
• EleutherAI / cookbook
  Deep learning for dummies. All the practical details and useful utilities that go into working with real models.
  ☆717Updated last month
• ruizheliUOA / Awesome-Interpretability-in-Large-Language-Models
  This repository collects all relevant resources about interpretability in LLMs
  ☆289Updated 3 weeks ago
• srush / LLM-Training-Puzzles
  What would you do with 1000 H100s...
  ☆910Updated 10 months ago
• huggingface / nanotron
  Minimalistic large language model 3D-parallelism training
  ☆1,265Updated this week
• stanfordnlp / pyreft
  ReFT: Representation Finetuning for Language Models
  ☆1,164Updated 2 weeks ago
• jxmorris12 / vec2text
  utilities for decoding deep representations (like sentence embeddings) back to text
  ☆737Updated 2 months ago
• ContextualAI / HALOs
  A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).
  ☆745Updated this week
• JonasGeiping / cramming
  Cramming the training of a (BERT-type) language model into limited compute.
  ☆1,296Updated 5 months ago
• EleutherAI / pythia
  The hub for EleutherAI's work on interpretability and learning dynamics
  ☆2,285Updated 3 weeks ago
• huggingface / lighteval
  Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends
  ☆813Updated this week
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆158Updated last month
• ai-safety-foundation / sparse_autoencoder
  Sparse Autoencoder for Mechanistic Interpretability
  ☆189Updated 4 months ago
• kmeng01 / rome
  Locating and editing factual associations in GPT (NeurIPS 2022)
  ☆576Updated 7 months ago
• ArthurConmy / Automatic-Circuit-Discovery
  ☆188Updated last month
• HoagyC / sparse_coding
  Using sparse coding to find distributed representations used by neural networks.
  ☆188Updated last year
• carlini / yet-another-applied-llm-benchmark
  A benchmark to evaluate language models on questions I've previously asked them to solve.
  ☆916Updated 2 weeks ago
• allenai / open-instruct
  ☆1,385Updated this week
• likenneth / honest_llama
  Inference-Time Intervention: Eliciting Truthful Answers from a Language Model
  ☆471Updated last month