4 papers
The Anatomy of Alignment: Decomposing Preference Optimization by Steering Sparse Features
Jeremias Ferrao, Matthijs van der Lende, Ilija Lichkovski +1
Prevailing alignment methods induce opaque parameter changes, obscuring what models truly learn. To address this, we introduce Feature Steering with Reinforcement Learning (FSRL),…
Beyond Monoliths: Expert Orchestration for More Capable, Democratic, and Safe Language Models
Philip Quirke, Narmeen Oozeer, Chaithanya Bandi +8
This position paper argues that the prevailing trajectory toward ever larger, more expensive generalist foundation models controlled by a handful of companies limits innovation and…
Understanding Refusal in Language Models with Sparse Autoencoders
Wei Jie Yeo, Nirmalendu Prakash, Clement Neo +3
Refusal is a key safety behavior in aligned language models, yet the internal mechanisms driving refusals remain opaque. In this work, we conduct a mechanistic study of refusal in…
TinySQL: A Progressive Text-to-SQL Dataset for Mechanistic Interpretability Research
Abir Harrasse, Philip Quirke, Clement Neo +3
Mechanistic interpretability research faces a gap between analyzing simple circuits in toy tasks and discovering features in large models. To bridge this gap, we propose text-to-SQ…