AlignmentResearch / tuned-lens

Related projects ⓘ

Alternatives and complementary repositories for tuned-lens

• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆198Updated 4 months ago
• collin-burns / discovering_latent_knowledge
  ☆253Updated 8 months ago
• ArthurConmy / Automatic-Circuit-Discovery
  ☆188Updated last month
• EleutherAI / concept-erasure
  Erasing concepts from neural representations with provable guarantees
  ☆209Updated last week
• jbloomAus / SAELens
  Training Sparse Autoencoders on Language Models
  ☆469Updated this week
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆157Updated last month
• EleutherAI / elk
  Keeping language models honest by directly eliciting knowledge encoded in their activations.
  ☆186Updated this week
• HoagyC / sparse_coding
  Using sparse coding to find distributed representations used by neural networks.
  ☆184Updated last year
• EleutherAI / sae
  Sparse autoencoders
  ☆342Updated last week
• kmeng01 / memit
  Mass-editing thousands of facts into a transformer memory (ICLR 2023)
  ☆438Updated 9 months ago
• saprmarks / feature-circuits
  ☆105Updated last month
• davidbau / baukit
  ☆170Updated 8 months ago
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆108Updated last year
• huggingface / datablations
  Scaling Data-Constrained Language Models
  ☆321Updated last month
• ndif-team / nnsight
  The nnsight package enables interpreting and manipulating the internals of deep learned models.
  ☆402Updated this week
• justinchiu / openlogprobs
  Extract full next-token probabilities via language model APIs
  ☆229Updated 8 months ago
• EleutherAI / sae-auto-interp
  ☆107Updated this week
• stanfordnlp / pyvene
  Stanford NLP Python Library for Understanding and Improving PyTorch Models via Interventions
  ☆641Updated 2 weeks ago
• likenneth / othello_world
  Emergent world representations: Exploring a sequence model trained on a synthetic task
  ☆169Updated last year
• openai / sparse_autoencoder
  ☆328Updated 4 months ago
• llm-efficiency-challenge / neurips_llm_efficiency_challenge
  NeurIPS Large Language Model Efficiency Challenge: 1 LLM + 1GPU + 1Day
  ☆252Updated last year
• nrimsky / CAA
  Steering Llama 2 with Contrastive Activation Addition
  ☆97Updated 5 months ago
• likenneth / honest_llama
  Inference-Time Intervention: Eliciting Truthful Answers from a Language Model
  ☆465Updated last month
• mcleish7 / arithmetic
  Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)
  ☆178Updated 5 months ago
• HazyResearch / zoology
  Understand and test language model architectures on synthetic tasks.
  ☆162Updated 6 months ago
• inseq-team / inseq
  Interpretability for sequence generation models 🐛 🔍
  ☆377Updated last week
• normster / llm_rules
  RuLES: a benchmark for evaluating rule-following in language models
  ☆211Updated last month
• redwoodresearch / Easy-Transformer
  ☆98Updated 3 months ago
• saprmarks / dictionary_learning
  ☆145Updated 3 weeks ago
• ruizheliUOA / Awesome-Interpretability-in-Large-Language-Models
  This repository collects all relevant resources about interpretability in LLMs
  ☆288Updated 2 weeks ago