AINeutralarXiv – CS AI · 10h ago7/10
🧠
Causal Dimensionality of Transformer Representations: Measurement, Scaling, and Layer Structure
Researchers introduce causal dimensionality (kappa), a measurable property quantifying how transformer layers causally influence model outputs, finding that representational capacity grows 15.6x faster than causal capacity across scaling conditions. The metric remains invariant to model size increases, suggesting causal influence is a fundamental architectural property independent of parameter count.