Transformer Field Theory frames the residual stream as a field, models patching as source insertion, and uses first-order sensitivities plus Green functions to predict and describe responses, with empirical tests on GPT-2 autoregressive models.
Statistical Dynamics of Classical Systems
6 Pith papers cite this work, alongside 1,964 external citations. Polarity classification is still indexing.
6
Pith papers citing it
1,964
external citations · OpenAlex
citation-role summary
background 1
citation-polarity summary
years
2026 6roles
background 1polarities
background 1representative citing papers
A source-extended Lie-group algorithm derives Ward identities for elastic Burgulence, showing viscoelastic turbulence has weaker symmetry constraints than Navier-Stokes turbulence.
DYNAMITE is a high-performance solver for dynamical mean-field equations that reaches times up to 10^7 with linear runtime and sublinear memory scaling.
sft-wick is a Python package and formalism that generates diagram tables and computes their integrals for stochastic field theories given an action and observable.
Non-conserved biased tracers debias more rapidly than conserved tracers, leading to time-dependent suppression of large-scale power.
Spacetime-symmetry-breaking Goldstone EFTs systematically describe bulk and localized excitations of solids, fluids, and superfluids, with new thermodynamic identifications and corrected scattering rates.
citing papers explorer
-
Transformer Field Theory: A Response-Theoretic Approach to Mechanistic Interpretability
Transformer Field Theory frames the residual stream as a field, models patching as source insertion, and uses first-order sensitivities plus Green functions to predict and describe responses, with empirical tests on GPT-2 autoregressive models.
-
Functional Renormalization for Elastic Burgulence
A source-extended Lie-group algorithm derives Ward identities for elastic Burgulence, showing viscoelastic turbulence has weaker symmetry constraints than Navier-Stokes turbulence.
-
DYNAMITE: A high-performance framework for solving Dynamical Mean-Field Equations
DYNAMITE is a high-performance solver for dynamical mean-field equations that reaches times up to 10^7 with linear runtime and sublinear memory scaling.
-
sft-wick: A formalism and package for Feynman-diagram expansion and evaluation in stochastic field theories
sft-wick is a Python package and formalism that generates diagram tables and computes their integrals for stochastic field theories given an action and observable.
-
Non-conservation and time non-locality of biased tracers
Non-conserved biased tracers debias more rapidly than conserved tracers, leading to time-dependent suppression of large-scale power.
-
Effective Field Theories for Material Media
Spacetime-symmetry-breaking Goldstone EFTs systematically describe bulk and localized excitations of solids, fluids, and superfluids, with new thermodynamic identifications and corrected scattering rates.