Publications

Relating Piecewise Linear Kolmogorov Arnold Networks to ReLU Networks

Jun 30, 2025

The Propensity for Density in Feed-forward Models

Aug 30, 2024

Dissecting Language Models: Machine Unlearning via Selective Pruning

Jun 30, 2024

Hidden in Plain Text: Emergence & Mitigation of Steganographic Collusion in LLMs

May 30, 2024

Extending Activation Steering to Broad Skills and Multiple Behaviours

Aug 26, 2023

Improving Activation Steering in Language Models with Mean-Centring

Jul 26, 2023

Any Deep ReLU Network is Shallow

Jun 26, 2023

Finding Sparse Initialisations using Neuroevolutionary Ticket Search (NeTS)

Jun 26, 2023