Institution profile

Beyond Institute for Theoretical Science

Academic institution
Research library1linked papers
Opportunities0open roles
Selected work

Representative Papers

Constrained belief updates explain geometric structures in transformer representations

Feb 04, 2025

This work investigates the emergent computational structures in Transformers performing next-token prediction and their explanatory mechanisms for representational geometric features. Method: We propose a theoretical framework of “architecture-constrained parallel Bayesian belief updating,” unifying optimal prediction principles with mechanistic interpretability. Leveraging hidden Markov model (HMM) construction, probability simplex analysis, attention inverse modeling, and constraint-based refinement of optimal prediction equations, we quantitatively predict attention distributions, OV-circuit vector orientations, and embedding manifold geometry. Contribution/Results: Our framework rigorously derives the geometric structure of attention patterns, OV-circuit vectors, and token embeddings, establishing their formal correspondence to Bayesian inference. On controlled HMM tasks, it successfully reproduces and explains canonical geometric representations—including cyclic dynamics and low-dimensional manifolds—demonstrating both quantitative accuracy and mechanistic interpretability of the theoretical predictions.

0 citationsRead paper
Recent publications

Latest Papers

Constrained belief updates explain geometric structures in transformer representations

Feb 04, 2025

This work investigates the emergent computational structures in Transformers performing next-token prediction and their explanatory mechanisms for representational geometric features. Method: We propose a theoretical framework of “architecture-constrained parallel Bayesian belief updating,” unifying optimal prediction principles with mechanistic interpretability. Leveraging hidden Markov model (HMM) construction, probability simplex analysis, attention inverse modeling, and constraint-based refinement of optimal prediction equations, we quantitatively predict attention distributions, OV-circuit vector orientations, and embedding manifold geometry. Contribution/Results: Our framework rigorously derives the geometric structure of attention patterns, OV-circuit vectors, and token embeddings, establishing their formal correspondence to Bayesian inference. On controlled HMM tasks, it successfully reproduces and explains canonical geometric representations—including cyclic dynamics and low-dimensional manifolds—demonstrating both quantitative accuracy and mechanistic interpretability of the theoretical predictions.

0 citationsRead paper