← Search

Tomáš Dulka

2 accepted papers

2025

A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders

NeurIPS 2025oral

Sparse Autoencoders (SAEs) aim to decompose the activation space of large language models (LLMs) into human-interpretable latent directions or features. As we increase the number of features in the SAE, hierarchical features tend to split into finer features (“math” may split into “algebra”, “geomet…

Cited by 0SourcecodeScholar
2023

EconBERTa: Towards Robust Extraction of Named Entities in Economics

EMNLP 2023long findings

Adapting general-purpose language models has proven to be effective in tackling downstream tasks within specific domains. In this paper, we address the task of extracting entities from the economics literature on impact evaluation. To this end, we release EconBERTa, a large language model pretrained…

Cited by 0SourceScholar