Staff profile
Overview
Patrick Leask
Postgraduate Student
| Affiliation |
|---|
| Postgraduate Student in the Department of Computer Science |
Publications
Conference Paper
- Inference-Time Decomposition of Activations (ITDA): A Scalable Approach to Interpreting Large Language ModelsLeask, P., & Al Moubayed, N. (in press). Inference-Time Decomposition of Activations (ITDA): A Scalable Approach to Interpreting Large Language Models. In Proceedings of Machine Learning Research.
- Sparse Autoencoders Do Not Find Canonical Units of AnalysisLeask, P., Bussmann, B., Pearce, M., Bloom, J., Tigges, C., Al Moubayed, N., Sharkey, L., & Nanda, N. (in press). Sparse Autoencoders Do Not Find Canonical Units of Analysis. Presented at ICLR2025: The Thirteenth International Conference on Learning Representations, Singapore.
- Sparse Autoencoders Do Not Find Canonical Units of AnalysisLeask, P., Bussmann, B., Pearce, M. T., Isaac Bloom, J., Tigges, C., Al Moubayed, N., Sharkey, L., & Nanda, N. (2025, January 22). Sparse Autoencoders Do Not Find Canonical Units of Analysis. Presented at The Thirteenth International Conference on Learning Representations, Singapore.