maxdreyer / PURELinks
Repository for PURE: Turning Polysemantic Neurons Into Pure Features by Identifying Relevant Circuits, accepted at CVPR 2024 XAI4CV Workshop (spotlight)
☆19Updated last year
Alternatives and similar repositories for PURE
Users that are interested in PURE are comparing it to the libraries listed below
Sorting:
- ☆49Updated 2 years ago
- Sparse Autoencoder Training Library☆55Updated 5 months ago
- 👋 Overcomplete is a Vision-based SAE Toolbox☆96Updated 2 months ago
- What do we learn from inverting CLIP models?☆55Updated last year
- Tools for optimizing steering vectors in LLMs.☆14Updated 6 months ago
- NeuroSurgeon is a package that enables researchers to uncover and manipulate subnetworks within models in Huggingface Transformers☆41Updated 8 months ago
- ☆108Updated 8 months ago
- [ICML 24] A novel automated neuron explanation framework that can accurately describe poly-semantic concepts in deep neural networks☆13Updated 5 months ago
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆136Updated 4 months ago
- ☆131Updated last week
- Steering vectors for transformer language models in Pytorch / Huggingface☆126Updated 8 months ago
- Spurious Features Everywhere - Large-Scale Detection of Harmful Spurious Features in ImageNet☆32Updated 2 years ago
- ☆191Updated 2 weeks ago
- Trains Sparse Autoencoders based on outputs from language models☆11Updated last year
- ☆15Updated 5 months ago
- ☆22Updated last year
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆25Updated 11 months ago
- ☆58Updated 2 years ago
- ☆54Updated 11 months ago
- ☆23Updated last year
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆219Updated last week
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆43Updated last year
- [NeurIPS 2025 MechInterp Workshop - Spotlight] Official implementation of the paper "RelP: Faithful and Efficient Circuit Discovery in La…☆16Updated this week
- ☆43Updated last year
- [ICLR 2025] Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"☆62Updated 4 months ago
- ☆34Updated 2 years ago
- ☆37Updated 10 months ago
- A fast, effective data attribution method for neural networks in PyTorch☆220Updated 11 months ago
- ☆23Updated 11 months ago
- A library for efficient patching and automatic circuit discovery.☆78Updated 3 months ago