Alternatives and similar repositories for PURE

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

• milesaturpin / cot-unfaithfulness
  ☆48Updated last year
• adamkarvonen / SAEBench
  ☆121Updated 2 months ago
• KihoPark / linear_rep_geometry
  ☆106Updated 7 months ago
• stanfordnlp / axbench
  Stanford NLP Python library for benchmarking the utility of LLM interpretability methods
  ☆128Updated 2 months ago
• slavachalnev / SAE-TS
  Improving Steering Vectors by Targeting Sparse Autoencoder Features
  ☆24Updated 9 months ago
• mlepori1 / NeuroSurgeon
  NeuroSurgeon is a package that enables researchers to uncover and manipulate subnetworks within models in Huggingface Transformers
  ☆41Updated 7 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 …
  ☆211Updated last week
• saprmarks / feature-circuits
  ☆186Updated 2 months ago
• noanabeshima / matryoshka-saes
  ☆23Updated 9 months ago
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆124Updated 6 months ago
• aengusl / latent-adversarial-training
  ☆43Updated 11 months ago
• jacobdunefsky / llm-steering-opt
  Tools for optimizing steering vectors in LLMs.
  ☆11Updated 5 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 4 months ago
• thestephencasper / benchmarking_interpretability
  ☆34Updated 2 years ago
• IBM / activation-steering
  [ICLR 2025] General-purpose activation steering library
  ☆102Updated 2 weeks ago
• KempnerInstitute / overcomplete
  👋 Overcomplete is a Vision-based SAE Toolbox
  ☆79Updated last month
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆76Updated last month
• thestephencasper / latent_adversarial_training
  ☆22Updated last year
• rishub-tamirisa / tamper-resistance
  [ICLR 2025] Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"
  ☆61Updated 3 months ago
• bartbussmann / matryoshka_sae
  ☆42Updated 8 months ago
• explanare / ravel
  Evaluate interpretability methods on localizing and disentangling concepts in LLMs.
  ☆54Updated 11 months ago
• Aaquib111 / edge-attribution-patching
  Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"
  ☆40Updated last year
• hamidkazemi22 / CLIPInversion
  What do we learn from inverting CLIP models?
  ☆55Updated last year
• ejones313 / auditing-llms
  ☆57Updated 2 years ago
• MaheepChaudhary / SAE-Ravel
  Providing the answer to "How to do patching on all available SAEs on GPT-2?". It is an official repository of the implementation of the p…
  ☆12Updated 7 months ago
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆54Updated 4 months ago
• locuslab / acr-memorization
  ☆37Updated 8 months ago
• gortizji / tangent_task_arithmetic
  Source code of "Task arithmetic in the tangent space: Improved editing of pre-trained models".
  ☆104Updated 2 years ago
• centerforaisafety / Intro_to_ML_Safety
  ☆74Updated 2 years ago
• serre-lab / Horama
  ☆15Updated 4 months ago