Alternatives and similar repositories for mats_sae_training_for_ViTs

Users that are interested in mats_sae_training_for_ViTs are comparing it to the libraries listed below

• neelnanda-io / Crosscoders
  ☆54Updated 10 months ago
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆127Updated last year
• KihoPark / linear_rep_geometry
  ☆106Updated 7 months ago
• vedantpalit / Towards-Vision-Language-Mechanistic-Interpretability
  This is the official repository for the "Towards Vision-Language Mechanistic Interpretability: A Causal Tracing Tool for BLIP" paper acce…
  ☆23Updated last year
• saprmarks / feature-circuits
  ☆187Updated 2 months ago
• adamkarvonen / SAEBench
  ☆125Updated 2 weeks ago
• science-of-finetuning / crosscoder_learning
  Modified to support crosscoder training.
  ☆23Updated 2 months ago
• slavachalnev / SAE-TS
  Improving Steering Vectors by Targeting Sparse Autoencoder Features
  ☆24Updated 10 months ago
• bartbussmann / BatchTopK
  Implementation of the BatchTopK activation function for training sparse autoencoders (SAEs)
  ☆48Updated 2 months ago
• ckkissane / crosscoder-model-diff-replication
  Open source replication of Anthropic's Crosscoders for Model Diffing
  ☆59Updated 11 months ago
• HoagyC / sparse_coding
  Using sparse coding to find distributed representations used by neural networks.
  ☆272Updated last year
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆77Updated 2 months ago
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆54Updated 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 …
  ☆215Updated this week
• nrimsky / CAA
  Steering Llama 2 with Contrastive Activation Addition
  ☆187Updated last year
• ArthurConmy / Automatic-Circuit-Discovery
  ☆242Updated last year
• saprmarks / dictionary_learning
  ☆347Updated last month
• jacobdunefsky / transcoder_circuits
  ☆174Updated 10 months ago
• Aaquib111 / edge-attribution-patching
  Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"
  ☆41Updated last year
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆221Updated 9 months ago
• adamkarvonen / dictionary_learning_demo
  ☆18Updated last month
• ai-safety-foundation / sparse_autoencoder
  Sparse Autoencoder for Mechanistic Interpretability
  ☆268Updated last year
• bilal-chughtai / rep-theory-mech-interp
  ☆27Updated 2 years ago
• noanabeshima / matryoshka-saes
  ☆23Updated 10 months ago
• redwoodresearch / Easy-Transformer
  ☆124Updated last year
• jbloomAus / SAEDashboard
  ☆71Updated last month
• saprmarks / geometry-of-truth
  ☆91Updated last year
• adamkarvonen / SAE_BoardGameEval
  ☆23Updated 8 months ago
• 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…
  ☆28Updated last year
• milesaturpin / cot-unfaithfulness
  ☆48Updated last year