Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Large Language Models Develop Belief State Geometry In-Context
Daniel Balcells, Andrew Jun Lee, Chirag Rastogi +3
Large language models (LLMs) trained on next-token prediction exhibit remarkable in-context learning (ICL) abilities, yet the representations that support ICL remain poorly underst…
cs.LG2024
Evolution of SAE Features Across Layers in LLMs
Daniel Balcells, Benjamin Lerner, Michael Oesterle +2
Sparse Autoencoders for transformer-based language models are typically defined independently per layer. In this work we analyze statistical relationships between features in adjac…