Alternatives and similar repositories for PURE

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

• milesaturpin / cot-unfaithfulness
  ☆47Updated last year
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆54Updated 3 months ago
• KempnerInstitute / overcomplete
  👋 Overcomplete is a Vision-based SAE Toolbox
  ☆76Updated 3 weeks ago
• YanNeu / spurious_imagenet
  Spurious Features Everywhere - Large-Scale Detection of Harmful Spurious Features in ImageNet
  ☆32Updated 2 years ago
• mlepori1 / NeuroSurgeon
  NeuroSurgeon is a package that enables researchers to uncover and manipulate subnetworks within models in Huggingface Transformers
  ☆41Updated 6 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 3 months ago
• rachtibat / LRP-eXplains-Transformers
  Layer-wise Relevance Propagation for Large Language Models and Vision Transformers [ICML 2024]
  ☆180Updated last month
• thestephencasper / latent_adversarial_training
  ☆22Updated last year
• KihoPark / linear_rep_geometry
  ☆103Updated 6 months ago
• ejones313 / auditing-llms
  ☆57Updated 2 years ago
• thestephencasper / benchmarking_interpretability
  ☆34Updated last year
• SchwinnL / circuit-breakers-eval
  Independent robustness evaluation of Improving Alignment and Robustness with Short Circuiting
  ☆18Updated 4 months ago
• hamidkazemi22 / CLIPInversion
  What do we learn from inverting CLIP models?
  ☆55Updated last year
• rishub-tamirisa / tamper-resistance
  [ICLR 2025] Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"
  ☆59Updated 2 months ago
• serre-lab / Horama
  ☆14Updated 3 months ago
• aengusl / latent-adversarial-training
  ☆41Updated 10 months ago
• adamkarvonen / SAEBench
  ☆114Updated last month
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆122Updated 6 months ago
• MadryLab / trak
  A fast, effective data attribution method for neural networks in PyTorch
  ☆217Updated 9 months ago
• tilde-research / activault
  Engine for collecting, uploading, and downloading model activations
  ☆22Updated 4 months ago
• stanfordnlp / axbench
  Stanford NLP Python library for benchmarking the utility of LLM interpretability methods
  ☆124Updated 2 months ago
• saprmarks / feature-circuits
  ☆184Updated last month
• 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
• locuslab / acr-memorization
  ☆36Updated 8 months ago
• PAIR-code / pretraining-tda
  ☆24Updated 6 months ago
• jacobdunefsky / llm-steering-opt
  Tools for optimizing steering vectors in LLMs.
  ☆11Updated 4 months ago
• ykwon0407 / DataInf
  DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models (ICLR 2024)
  ☆74Updated 10 months ago
• slavachalnev / SAE-TS
  Improving Steering Vectors by Targeting Sparse Autoencoder Features
  ☆24Updated 9 months ago
• vasusingla / simple-data-attribution
  A simple and efficient baseline for data attribution
  ☆11Updated last year
• explanare / ravel
  Evaluate interpretability methods on localizing and disentangling concepts in LLMs.
  ☆53Updated 10 months ago