Rare-token specialists in GPT-2 XL and Pythia are spatially scattered and accessed by generic attention, not modular clusters or dedicated routing.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
No Clustering, No Routing: How Transformers Actually Process Rare Tokens
Rare-token specialists in GPT-2 XL and Pythia are spatially scattered and accessed by generic attention, not modular clusters or dedicated routing.