Alternatives and similar repositories for codebook-features:

Users that are interested in codebook-features are comparing it to the libraries listed below

• jacobdunefsky / transcoder_circuits
  ☆61Updated 4 months ago
• callummcdougall / sae_visualizer
  ☆26Updated 11 months ago
• epfml / schedules-and-scaling
  Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"
  ☆71Updated 4 months ago
• EleutherAI / w2s
  ☆21Updated 5 months ago
• EleutherAI / delphi
  Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …
  ☆161Updated this week
• EleutherAI / elk-generalization
  Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…
  ☆26Updated 9 months ago
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆43Updated 4 months ago
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆90Updated last month
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆121Updated last year
• shauli-ravfogel / rlace-icml
  ☆35Updated 2 years ago
• bilal-chughtai / rep-theory-mech-interp
  ☆26Updated last year
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆59Updated last month
• google-deepmind / mishax
  ☆124Updated this week
• wesg52 / universal-neurons
  Universal Neurons in GPT2 Language Models
  ☆27Updated 9 months ago
• KoyenaPal / future-lens
  Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State
  ☆18Updated last year
• TomFrederik / unseal
  Mechanistic Interpretability for Transformer Models
  ☆50Updated 2 years ago
• mlfoundations / scaling
  Language models scale reliably with over-training and on downstream tasks
  ☆96Updated 11 months ago
• JoshEngels / SAE-Dark-Matter
  Code for our paper "Decomposing The Dark Matter of Sparse Autoencoders"
  ☆21Updated last month
• microsoft / mechanistic-error-probe
  A mechanistic approach for understanding and detecting factual errors of large language models.
  ☆41Updated 8 months ago
• KaiNylund / lm-weights-encode-time
  ☆67Updated 7 months ago
• KihoPark / LLM_Categorical_Hierarchical_Representations
  ☆89Updated last month
• jbloomAus / SAEDashboard
  ☆34Updated 3 weeks ago
• aryamanarora / causalgym
  CausalGym: Benchmarking causal interpretability methods on linguistic tasks
  ☆41Updated 3 months ago
• METR / RE-Bench
  ☆65Updated last month
• redwoodresearch / Easy-Transformer
  ☆113Updated 7 months ago
• meg-tong / sycophancy-eval
  datasets from the paper "Towards Understanding Sycophancy in Language Models"
  ☆73Updated last year
• KhoomeiK / complexity-scaling
  gzip Predicts Data-dependent Scaling Laws
  ☆34Updated 9 months ago
• ethancaballero / broken_neural_scaling_laws
  Code Release for "Broken Neural Scaling Laws" (BNSL) paper
  ☆58Updated last year
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆189Updated 3 months ago