maxdreyer / PURELinks
Repository for PURE: Turning Polysemantic Neurons Into Pure Features by Identifying Relevant Circuits, accepted at CVPR 2024 XAI4CV Workshop (spotlight)
☆14Updated last year
Alternatives and similar repositories for PURE
Users that are interested in PURE are comparing it to the libraries listed below
Sorting:
- ☆11Updated last month
- Spurious Features Everywhere - Large-Scale Detection of Harmful Spurious Features in ImageNet☆32Updated last year
- 👋 Overcomplete is a Vision-based SAE Toolbox☆57Updated 2 months ago
- What do we learn from inverting CLIP models?☆54Updated last year
- A toolkit for quantitative evaluation of data attribution methods.☆47Updated last month
- ☆22Updated 10 months ago
- 👋 Code for : "CRAFT: Concept Recursive Activation FacTorization for Explainability" (CVPR 2023)☆64Updated last year
- MetaQuantus is an XAI performance tool to identify reliable evaluation metrics☆34Updated last year
- ☆34Updated last year
- Pytorch ImageNet1k Loader with Bounding Boxes.☆12Updated 3 years ago
- Intriguing Properties of Data Attribution on Diffusion Models (ICLR 2024)☆30Updated last year
- [ICML 24] A novel automated neuron explanation framework that can accurately describe poly-semantic concepts in deep neural networks☆12Updated last month
- ☆25Updated 3 months ago
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆89Updated last week
- Code for the ICLR 2022 paper. Salient Imagenet: How to discover spurious features in deep learning?☆40Updated 2 years ago
- ☆44Updated last year
- NeuroSurgeon is a package that enables researchers to uncover and manipulate subnetworks within models in Huggingface Transformers