Leslie, Sarah-Jane

3 publications

ICLR 2026 Learning Is Forgetting; LLM Training as Lossy Compression Henry Conklin, Tom Hosking, Tan Yi-Chern, Jonathan D. Cohen, Sarah-Jane Leslie, Thomas L. Griffiths, Max Bartolo, Seraphina Goldfarb-Tarrant

NeurIPS 2025 Causal Head Gating: A Framework for Interpreting Roles of Attention Heads in Transformers Andrew Joohun Nam, Henry Conklin, Yukang Yang, Thomas L. Griffiths, Jonathan D. Cohen, Sarah-Jane Leslie

ICLRW 2025 Understanding Task Representations in Neural Networks via Bayesian Ablation Andrew Joohun Nam, Declan Iain Campbell, Thomas L. Griffiths, Jonathan D. Cohen, Sarah-Jane Leslie