Alternatives and similar repositories for PURE

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

• KempnerInstitute / overcomplete
  👋 Overcomplete is a Vision-based SAE Toolbox
  ☆106Updated last week
• jacobdunefsky / llm-steering-opt
  Tools for optimizing steering vectors in LLMs.
  ☆15Updated 8 months ago
• adamkarvonen / SAEBench
  ☆136Updated 3 weeks ago
• milesaturpin / cot-unfaithfulness
  ☆51Updated 2 years ago
• mlepori1 / NeuroSurgeon
  NeuroSurgeon is a package that enables researchers to uncover and manipulate subnetworks within models in Huggingface Transformers
  ☆42Updated 9 months ago
• IBM / activation-steering
  [ICLR 2025] General-purpose activation steering library
  ☆127Updated 2 months ago
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆55Updated 7 months ago
• thestephencasper / benchmarking_interpretability
  ☆35Updated 2 years 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 …
  ☆231Updated last week
• stanfordnlp / axbench
  Stanford NLP Python library for benchmarking the utility of LLM interpretability methods
  ☆151Updated 5 months ago
• serre-lab / Horama
  ☆16Updated 7 months ago
• efarrell1 / train_sparse_autoencoder
  Trains Sparse Autoencoders based on outputs from language models
  ☆12Updated last year
• rishub-tamirisa / tamper-resistance
  [ICLR 2025] Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"
  ☆65Updated 6 months ago
• saprmarks / feature-circuits
  ☆196Updated last month
• wesg52 / universal-neurons
  Universal Neurons in GPT2 Language Models
  ☆31Updated last year
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆130Updated 9 months ago
• peterljq / Parsimonious-Concept-Engineering
  PaCE: Parsimonious Concept Engineering for Large Language Models (NeurIPS 2024)
  ☆41Updated last year
• KihoPark / linear_rep_geometry
  ☆111Updated 10 months ago
• Trustworthy-ML-Lab / Linear-Explanations
  [ICML 24] A novel automated neuron explanation framework that can accurately describe poly-semantic concepts in deep neural networks
  ☆13Updated 7 months ago
• Aaquib111 / edge-attribution-patching
  Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"
  ☆43Updated last year
• hamidkazemi22 / CLIPInversion
  What do we learn from inverting CLIP models?
  ☆57Updated last year
• neelnanda-io / Crosscoders
  ☆58Updated last year
• slavachalnev / SAE-TS
  Improving Steering Vectors by Targeting Sparse Autoencoder Features
  ☆24Updated last year
• ai-safety-foundation / sparse_autoencoder
  Sparse Autoencoder for Mechanistic Interpretability
  ☆284Updated last year
• noanabeshima / matryoshka-saes
  ☆25Updated last year
• MadryLab / trak
  A fast, effective data attribution method for neural networks in PyTorch
  ☆222Updated last year
• tilde-research / activault
  Engine for collecting, uploading, and downloading model activations
  ☆24Updated 8 months ago
• explanare / ravel
  Evaluate interpretability methods on localizing and disentangling concepts in LLMs.
  ☆57Updated last month
• amack315 / unsupervised-steering-vectors
  ☆36Updated last year
• rachtibat / LRP-eXplains-Transformers
  Layer-wise Relevance Propagation for Large Language Models and Vision Transformers [ICML 2024]
  ☆211Updated 5 months ago