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
  ☆39Updated 5 months ago
• slavachalnev / SAE-TS
  Improving Steering Vectors by Targeting Sparse Autoencoder Features
  ☆18Updated 5 months ago
• KihoPark / linear_rep_geometry
  ☆92Updated 2 months ago
• adamkarvonen / SAEBench
  ☆93Updated 3 weeks ago
• ckkissane / crosscoder-model-diff-replication
  Open source replication of Anthropic's Crosscoders for Model Diffing
  ☆54Updated 6 months ago
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆49Updated this week
• jbloomAus / SAEDashboard
  ☆38Updated 2 months ago
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆121Updated last year
• tim-lawson / mlsae
  Multi-Layer Sparse Autoencoders (ICLR 2025)
  ☆23Updated 2 months ago
• saprmarks / feature-circuits
  ☆164Updated 3 weeks ago
• tilde-research / sieve
  Applying SAEs for fine-grained control
  ☆17Updated 4 months ago
• HoagyC / sparse_coding
  Using sparse coding to find distributed representations used by neural networks.
  ☆240Updated last year
• callummcdougall / sae_visualizer
  ☆26Updated last year
• EleutherAI / delphi
  Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …
  ☆170Updated last week
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆64Updated 2 weeks ago
• adamkarvonen / dictionary_learning_demo
  ☆11Updated last month
• montemac / activation_additions
  Algebraic value editing in pretrained language models
  ☆64Updated last year
• bartbussmann / BatchTopK
  Implementation of the BatchTopK activation function for training sparse autoencoders (SAEs)
  ☆37Updated 7 months ago
• amack315 / unsupervised-steering-vectors
  ☆31Updated last year
• jacobdunefsky / transcoder_circuits
  ☆111Updated 5 months ago
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆99Updated 2 months ago
• ArthurConmy / Automatic-Circuit-Discovery
  ☆221Updated 7 months ago
• JoshEngels / MultiDimensionalFeatures
  Code for reproducing our paper "Not All Language Model Features Are Linear"
  ☆73Updated 5 months ago
• Aaquib111 / edge-attribution-patching
  Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"
  ☆31Updated 11 months ago
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆199Updated 4 months ago
• nrimsky / CAA
  Steering Llama 2 with Contrastive Activation Addition
  ☆147Updated 11 months ago
• mlepori1 / NeuroSurgeon
  NeuroSurgeon is a package that enables researchers to uncover and manipulate subnetworks within models in Huggingface Transformers
  ☆41Updated 2 months ago
• explanare / ravel
  Evaluate interpretability methods on localizing and disentangling concepts in LLMs.
  ☆46Updated 7 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…
  ☆26Updated 11 months ago
• curt-tigges / probity
  ☆12Updated 3 weeks ago