Publications (5)
Enumerating Galois representations in Sage
Craig Citro, Alexandru Ghitza
We present an algorithm for enumerating all odd semisimple two-dimensional mod p Galois representations unramified outside p. We also discuss the implementation of this algorithm i…
Computing level one Hecke eigensystems (mod p)
Craig Citro, Alexandru Ghitza
We describe an algorithm for enumerating the set of level 1 systems of Hecke eigenvalues arising from modular forms (mod p).
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…
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…
TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
MartÃn Abadi, Ashish Agarwal, Paul Barham +37
TensorFlow is an interface for expressing machine learning algorithms, and an implementation for executing such algorithms. A computation expressed using TensorFlow can be executed…