25 citations · 25 across the 4 of their papers we have counts for
6 papers
LLMs program using Reusable and Composable Abstract Representations
Casper L. Christensen, Kyle J. Ray, Dmitry Manning-Coe +2
When writing code, the same computation can be expressed in different programming languages and through different implementation strategies. We show that the activations of LLMs ca…
Interactions Between Crosscoder Features: A Compact Proofs Perspective
Dmitry Manning-Coe, Thomas Read, Anna Soligo +4
Dictionary learning methods like Sparse Autoencoders (SAEs) and crosscoders attempt to explain a model by decomposing its activations into independent features. Interactions betwee…
Decomposing momentum scales in the Hubbard Model: From Hatsugai-Kohmoto to Aubry-André
Dmitry Manning-Coe, Barry Bradlyn
The all-to-all momentum coupling of the Hubbard interaction makes interacting lattice models generically unsolvable. In many settings, however, from Peierls instabilities to Moiré…
Grokking vs. Learning: Same Features, Different Encodings
Dmitry Manning-Coe, Jacopo Gliozzi, Alexander G. Stapleton +4
Grokking typically achieves similar loss to ordinary, "steady", learning. We ask whether these different learning paths - grokking versus ordinary training - lead to fundamental di…
Ground state stability, symmetry, and degeneracy in Mott insulators with long range interactions
Dmitry Manning-Coe, Barry Bradlyn
Recently, models with long-range interactions -- known as Hatsugai-Kohmoto (HK) models -- have emerged as a promising tool to study the emergence of superconductivity and topology…
Lattices: From Roots to String Compactifications
Dmitry Manning-Coe
In this dissertation we attempt to answer the question of whether non-abelian gauge groups occur in all F-theory models with Picard number 20 and with a Calabi-Yau four-fold CY4 K3…