papers

Publications (14)

math.GT2012

Nonorientable four-ball genus can be arbitrarily large

Joshua Batson

The nonorientable four-ball genus of a knot K is the smallest first Betti number of any smoothly embedded, nonorientable surface F in B^4 bounding K. In contrast to the orientable…

cs.LG2025

Open Problems in Mechanistic Interpretability

Lee Sharkey, Bilal Chughtai, Joshua Batson +26

Mechanistic interpretability aims to understand the computational mechanisms underlying neural networks' capabilities in order to accomplish concrete scientific and engineering goa…

cs.LG2020

Patch2Self: Denoising Diffusion MRI with Self-Supervised Learning

Shreyas Fadnavis, Joshua Batson, Eleftherios Garyfallidis

Diffusion-weighted magnetic resonance imaging (DWI) is the only noninvasive method for quantifying microstructure and reconstructing white-matter pathways in the living human brain…

cs.AI2025

Auditing language models for hidden objectives

Samuel Marks, Johannes Treutlein, Trenton Bricken +32

We study the feasibility of conducting alignment audits: investigations into whether models have undesired objectives. As a testbed, we train a language model with a hidden objecti…

math.QA2013

A Link Splitting Spectral Sequence in Khovanov Homology

Joshua Batson, Cotton Seed

We construct a new spectral sequence beginning at the Khovanov homology of a link and converging to the Khovanov homology of the disjoint union of its components. The page at which…

cs.CL2026

Verbalizable Representations Form a Global Workspace in Language Models

Wes Gurnee, Nicholas Sofroniew, Adam Pearce +13

Out of everything the human brain processes, only a small fraction is consciously accessible, in the sense of being available for verbal report, deliberate control, and flexible re…

hep-ph2021

Topological Obstructions to Autoencoding

Joshua Batson, C. Grace Haaf, Yonatan Kahn +1

Autoencoders have been proposed as a powerful tool for model-independent anomaly detection in high-energy physics. The operating principle is that events which do not belong to the…

cs.AI2026

Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet

Adly Templeton, Tom Conerly, Jonathan Marcus +23

We demonstrate that sparse autoencoders can extract interpretable features from Claude 3 Sonnet, a production-scale language model, addressing the open question of whether dictiona…

cs.AI2026

Emotion Concepts and their Function in a Large Language Model

Nicholas Sofroniew, Isaac Kauvar, William Saunders +13

Large language models (LLMs) sometimes appear to exhibit emotional reactions. We investigate why this is the case in Claude Sonnet 4.5 and explore implications for alignment-releva…

cs.DS2009

Twice-Ramanujan Sparsifiers

Joshua Batson, Daniel A. Spielman, Nikhil Srivastava

We prove that every graph has a spectral sparsifier with a number of edges linear in its number of vertices. As linear-sized spectral sparsifiers of complete graphs are expanders,…

hep-ph2023

Scaling Laws in Jet Classification

Joshua Batson, Yonatan Kahn

We demonstrate the emergence of scaling laws in the benchmark top versus QCD jet classification problem in collider physics. Six distinct physically-motivated classifiers exhibit p…

cs.CV2020

Image Deconvolution via Noise-Tolerant Self-Supervised Inversion

Hirofumi Kobayashi, Ahmet Can Solak, Joshua Batson +1

We propose a general framework for solving inverse problems in the presence of noise that requires no signal prior, no noise estimate, and no clean training data. We only require t…

cs.CV2019

Noise2Self: Blind Denoising by Self-Supervision

Joshua Batson, Loic Royer

We propose a general framework for denoising high-dimensional measurements which requires no prior on the signal, no estimate of the noise, and no clean training data. The only ass…

cs.LG2026

When Models Manipulate Manifolds: The Geometry of a Counting Task

Wes Gurnee, Emmanuel Ameisen, Isaac Kauvar +4

Language models can perceive visual properties of text despite receiving only sequences of tokens-we mechanistically investigate how Claude 3.5 Haiku accomplishes one such task: li…