40 citations · 41 across the 7 of their papers we have counts for
Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
Comparing Sparsified MLPs and Transcoders: Many Transcoder Features Are Neurons in Disguise
Stepan Shabalin, Mateusz Piotrowski
MLP neurons in transformer language models are widely understood to be polysemantic, motivating transcoders - sparse, learned approximations of MLP layers - as interpretable replac…
cs.AI2025
Patterns and Mechanisms of Contrastive Activation Engineering
Yixiong Hao, Ayush Panda, Stepan Shabalin +1
Controlling the behavior of Large Language Models (LLMs) remains a significant challenge due to their inherent complexity and opacity. While techniques like fine-tuning can modify…