Repository for PURE: Turning Polysemantic Neurons Into Pure Features by Identifying Relevant Circuits, accepted at CVPR 2024 XAI4CV Workshop (spotlight)
☆20Aug 30, 2026Updated 2 months ago
Alternatives and similar repositories for PURE
Users that are interested in PURE are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Prototypical Concept-based Explanations, accepted at SAIAD workshop at CVPR 2024.☆17Aug 30, 2026Updated 2 months ago
- Concept Relevance Propagation for Localization Models, accepted at SAIAD workshop at CVPR 2023.☆17Jan 16, 2024Updated 2 years ago
- Reveal to Revise: An Explainable AI Life Cycle for Iterative Bias Correction of Deep Models. Paper presented at MICCAI 2023 conference.☆19Jan 17, 2024Updated 2 years ago
- PyPI package for DualXDA for efficient data attribution and feature-level explanations of training data influence☆22Mar 6, 2026Updated 7 months ago
- ☆18Updated this week
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- ☆12Aug 27, 2025Updated last year
- [NeurIPS 2025] PRISM is a multi-concept feature description framework which can identify and score polysemantic features.☆14Jun 26, 2026Updated 4 months ago
- ☆15Nov 3, 2025Updated 11 months ago
- True-color terminal image visualization library with command-line interface for python☆10Dec 3, 2024Updated last year
- An eXplainable AI toolkit with Concept Relevance Propagation and Relevance Maximization☆141Jan 14, 2026Updated 9 months ago
- CoRelAy is a tool to compose small-scale (single-machine) analysis pipelines.☆30Apr 30, 2026Updated 6 months ago
- Layer-wise Relevance Propagation for Large Language Models and Vision Transformers [ICML 2024]☆256Aug 11, 2026Updated 2 months ago
- Code for "Don't trust your eyes: on the (un)reliability of feature visualizations" (ICML 2024)☆33Nov 15, 2023Updated 2 years ago
- Mechanistic understanding and validation of large AI models with SemanticLens☆55Aug 23, 2026Updated 2 months ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Pruning CNN using CNN with toy example☆23Jun 21, 2021Updated 5 years ago
- Pruning By Explaining Revisited: Optimizing Attribution Methods to Prune CNNs and Transformers, Paper accepted at eXCV workshop of ECCV 2…☆32Jan 6, 2025Updated last year
- Repository for "From What to How: Attributing CLIP's Latent Components Reveals Unexpected Semantic Reliance"☆11Jun 8, 2025Updated last year
- [TMLR 25] An automated method for explaining complex neuron behaviors in deep vision models using large language models☆12Feb 20, 2025Updated last year
- [ICML 24] A novel automated neuron explanation framework that can accurately describe poly-semantic concepts in deep neural networks☆14May 2, 2025Updated last year
- ViT Prisma is a mechanistic interpretability library for Vision and Video Transformers (ViTs).☆397Oct 7, 2026Updated 3 weeks ago
- A tiny easily hackable implementation of a feature dashboard.☆18Oct 21, 2025Updated last year
- A ViT model that allows comparing text embeddings directly with image patch embeddings☆13Mar 10, 2025Updated last year
- ☆14Jun 12, 2023Updated 3 years ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Repository for the Feature Alignment to Descriptions Evaluation (FADE) Paper☆11Feb 10, 2026Updated 8 months ago
- Subliminal learning in LLMs: language models can transmit hidden preferences through seemingly unrelated training data.☆25Nov 9, 2025Updated 11 months ago
- ☆12Aug 25, 2022Updated 4 years ago
- ☆21May 1, 2025Updated last year
- This is the official repository for the "Towards Vision-Language Mechanistic Interpretability: A Causal Tracing Tool for BLIP" paper acce…☆25Feb 16, 2026Updated 8 months ago
- Official code for "Can We Talk Models Into Seeing the World Differently?" (ICLR 2025).☆30Jan 26, 2025Updated last year
- Code for Overinterpretation paper☆19Jul 6, 2023Updated 3 years ago
- MetaQuantus is an XAI performance tool to identify reliable evaluation metrics☆46Apr 17, 2024Updated 2 years ago
- Official Implementation of TMLR's paper: "TabCBM: Concept-based Interpretable Neural Networks for Tabular Data"☆16Apr 4, 2024Updated 2 years ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- [NeurIPS 2025] Interpreting vision transformers via residual replacement model☆22Nov 3, 2025Updated 11 months ago
- Implementation of the paper "Improving the Accuracy-Robustness Trade-off of Classifiers via Adaptive Smoothing".☆10Feb 6, 2024Updated 2 years ago
- Fast RDF serialization for Python☆22Updated this week
- Code for the paper "Scattering Model Guided Adversarial Examples for SAR Target Recognition: Attack and Defense".☆12Dec 23, 2025Updated 10 months ago
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆30Nov 20, 2024Updated last year
- 👋 Overcomplete is a Vision-based SAE Toolbox☆155Dec 4, 2025Updated 10 months ago
- ☆42Sep 5, 2023Updated 3 years ago