Alternatives and similar repositories for PURE

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

• milesaturpin / cot-unfaithfulness
  ☆51Updated 2 years ago
• KempnerInstitute / overcomplete
  👋 Overcomplete is a Vision-based SAE Toolbox
  ☆119Updated 2 months ago
• mlepori1 / NeuroSurgeon
  NeuroSurgeon is a package that enables researchers to uncover and manipulate subnetworks within models in Huggingface Transformers
  ☆42Updated 11 months ago
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆56Updated 9 months ago
• thestephencasper / benchmarking_interpretability
  ☆35Updated 2 years ago
• KihoPark / linear_rep_geometry
  ☆116Updated 11 months ago
• efarrell1 / train_sparse_autoencoder
  Trains Sparse Autoencoders based on outputs from language models
  ☆11Updated last year
• hamidkazemi22 / CLIPInversion
  What do we learn from inverting CLIP models?
  ☆58Updated last year
• aengusl / latent-adversarial-training
  ☆47Updated last year
• serre-lab / Horama
  ☆16Updated 9 months ago
• locuslab / acr-memorization
  ☆37Updated last year
• Trustworthy-ML-Lab / Linear-Explanations
  [ICML 24] A novel automated neuron explanation framework that can accurately describe poly-semantic concepts in deep neural networks
  ☆14Updated 9 months ago
• jacobdunefsky / llm-steering-opt
  Tools for optimizing steering vectors in LLMs.
  ☆19Updated 10 months ago
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆88Updated last month
• YanNeu / spurious_imagenet
  Spurious Features Everywhere - Large-Scale Detection of Harmful Spurious Features in ImageNet
  ☆32Updated 2 years ago
• stanfordnlp / axbench
  Stanford NLP Python library for benchmarking the utility of LLM interpretability methods
  ☆163Updated 7 months ago
• Aaquib111 / edge-attribution-patching
  Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"
  ☆47Updated last year
• slavachalnev / SAE-TS
  Improving Steering Vectors by Targeting Sparse Autoencoder Features
  ☆26Updated last year
• adamkarvonen / SAEBench
  ☆143Updated last month
• saprmarks / feature-circuits
  ☆206Updated 3 months ago
• ApolloResearch / deception-detection
  ☆33Updated 11 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 …
  ☆241Updated 2 weeks ago
• thestephencasper / latent_adversarial_training
  ☆24Updated last year
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆140Updated 11 months ago
• ejones313 / auditing-llms
  ☆60Updated 2 years ago
• bartbussmann / matryoshka_sae
  ☆58Updated last year
• fiveai / understanding_safety_finetuning
  Official Code for What Makes and Breaks Safety Fine-tuning? A Mechanistic Study (NeurIPS 2024)
  ☆12Updated last year
• IBM / activation-steering
  [ICLR 2025] General-purpose activation steering library
  ☆141Updated 4 months ago
• FlyingPumba / InterpBench
  A benchmark for mechanistic discovery of circuits in Transformers
  ☆16Updated last year
• ApolloResearch / apd
  Attribution-based Parameter Decomposition
  ☆33Updated 7 months ago