FarnoushRJ / RelPLinks
Official implementation of the paper "RelP: Faithful and Efficient Circuit Discovery via Relevance Patching"
☆15Updated last month
Alternatives and similar repositories for RelP
Users that are interested in RelP are comparing it to the libraries listed below
Sorting:
- NeuroSurgeon is a package that enables researchers to uncover and manipulate subnetworks within models in Huggingface Transformers☆41Updated 7 months ago
- Repository for PURE: Turning Polysemantic Neurons Into Pure Features by Identifying Relevant Circuits, accepted at CVPR 2024 XAI4CV Works…☆19Updated last year
- Measuring the Mixing of Contextual Information in the Transformer☆31Updated 2 years ago
- ☆26Updated 7 months ago
- ☆125Updated 2 weeks ago
- Layer-wise Relevance Propagation for Large Language Models and Vision Transformers [ICML 2024]☆192Updated 2 months ago
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆56Updated last year
- Materials for EACL2024 tutorial: Transformer-specific Interpretability☆60Updated last year
- ☆81Updated 7 months ago
- ☆18Updated last month
- ☆106Updated 7 months ago
- Sparse probing paper full code.☆61Updated last year
- ☆51Updated 2 months ago
- Unified access to Large Language Model modules using NNsight☆48Updated this week
- ☆48Updated last year
- ☆348Updated last month
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆41Updated last year
- Engine for collecting, uploading, and downloading model activations☆24Updated 6 months ago
- ☆26Updated last year
- Influence Functions with (Eigenvalue-corrected) Kronecker-Factored Approximate Curvature☆165Updated 3 months ago
- 👋 Overcomplete is a Vision-based SAE Toolbox☆90Updated 2 months ago
- Landing page for MIB: A Mechanistic Interpretability Benchmark☆20Updated last month
- ☆187Updated 2 months ago
- ☆22Updated 5 months ago
- Sparse Autoencoder for Mechanistic Interpretability☆268Updated last year
- ☆22Updated this week
- [ICLR 2025] General-purpose activation steering library☆108Updated 3 weeks ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆59Updated 11 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆125Updated 7 months ago
- A benchmark for mechanistic discovery of circuits in Transformers☆16Updated 9 months ago