2 papers
cs.LG2024
The Propensity for Density in Feed-forward Models
Nandi Schoots, Alex Jackson, Ali Kholmovaia +2
Does the process of training a neural network to solve a task tend to use all of the available weights even when the task could be solved with fewer weights? To address this questi…
cs.CL2023
Improving Activation Steering in Language Models with Mean-Centring
Ole Jorgensen, Dylan Cope, Nandi Schoots +1
Recent work in activation steering has demonstrated the potential to better control the outputs of Large Language Models (LLMs), but it involves finding steering vectors. This is d…