Tag
This paper traces how subject–verb number agreement circuits emerge and sparsify across training in Pythia-1b and Pythia-410m models, finding that behavior stabilizes early while the underlying circuit keeps reorganizing, shifting attention heads, and shrinking to a strikingly sparse final form.
This research investigates how multilingual large language models internally handle subject-verb agreement across languages, finding that models reuse shared computational structure for languages with overt inflection, indicating cross-lingual overlap in morphosyntactic processing.