2 papers
cs.CL2026
Sparse Feature Coactivation Reveals Causal Semantic Modules in Large Language Models
Ruixuan Deng, Xiaoyang Hu, Miles Gilberti +5
We identify semantically coherent, context-consistent network components in large language models (LLMs) using coactivation of sparse autoencoder (SAE) features collected from just…
cs.CL2025
Discovering Properties of Inflectional Morphology in Neural Emergent Communication
Miles Gilberti, Shane Storks, Huteng Dai
Emergent communication (EmCom) with deep neural network-based agents promises to yield insights into the nature of human language, but remains focused primarily on a few subfield-s…