Transformer circuits show free evolution during SFT, rendering static mechanistic localization inadequate for future parameter updates due to inherent temporal latency.
Visualizing and understanding neural models in nlp
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Analysis of Glauber dynamics on masked language models shows O(n log n) mixing under bounded cross-token influence and metastability with exponential escape times at low temperatures, plus empirical phase transitions.
citing papers explorer
-
Navigating by Old Maps: The Pitfalls of Static Mechanistic Localization in LLM Post-Training
Transformer circuits show free evolution during SFT, rendering static mechanistic localization inadequate for future parameter updates due to inherent temporal latency.
-
Mixing Times of Glauber Dynamics on Masked Language Models
Analysis of Glauber dynamics on masked language models shows O(n log n) mixing under bounded cross-token influence and metastability with exponential escape times at low temperatures, plus empirical phase transitions.