Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models
Marks, Samuel, Can Rager, Eric J. Michaud, Yonatan Belinkov, David Bau, Aaron Mueller
Who it is from
Northeastern Universityaffiliation declared by the authors, according to OpenAlex
Other papers from the same organizations
- Kolmogorov-Arnold Networks Meet ScienceHarvard University · 687 citations
- Mental-LLM: Leveraging Large Language Models for Mental Health Prediction via Online Text DataNortheastern University · 658 citations
- Unified Concept Editing in Diffusion ModelsNortheastern University · 546 citations
- VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality DocumentsNortheastern University · 297 citations
- Improving LoRA in Privacy-preserving Federated LearningNortheastern University · 245 citations