Language models obtain extensive capabilities through pre-training. However, the pre-training process remains a black box. In this work, we track linear interpretable feature evolution across pre-training snapshots using a sparse dictionary learning method called crosscoders. We find that most features begin to form around a specific point, while more complex patterns emerge in later training stages. Feature attribution analyses reveal causal connections between feature evolution and downstream performance. Our feature-level observations are highly consistent with previous findings on Transformer's two-stage learning process, which we term a statistical learning phase and a feature learning phase. Our work opens up the possibility to track fine-grained representation progress during language model learning dynamics.
@article{arxiv.2509.17196,
title = {Evolution of Concepts in Language Model Pre-Training},
author = {Xuyang Ge and Wentao Shu and Jiaxing Wu and Yunhua Zhou and Zhengfu He and Xipeng Qiu},
journal= {arXiv preprint arXiv:2509.17196},
year = {2026}
}