The Geometry of Nonergodic Composition
Crossposted from Belief Updates, the Simplex blog, where several of the figures are interactive. By Kyle J. Ray, Paul M. Riechers, and Adam S. Shai (Simplex, Astera Institute). Telescoping cones recovered by linear regression from a transformer’s residual-stream activations. Each component grows and shrinks in accordance with in-context evidence. Introduction Perhaps the defining feature of LLM pretraining data is its heterogeneity. The training corpus spans not only the collected and varied tex...
Read full article →