3 papers
cs.CL2026
Some Tokens Behave like Magnets: Revealing Linguistic Organization in the Layers of Language Models
Andrew Liu, Devan Srinivasan, Gerald Penn
We identify a special group of token vectors inside large language models (LLMs), which we term magnetic vectors, that organize the surrounding tokens by either attracting or repel…
cs.CL2024
Sheaf Discovery with Joint Computation Graph Pruning and Flexible Granularity
Lei Yu, Jingcheng Niu, Zining Zhu +2
In this paper, we introduce DiscoGP, a novel framework for extracting self-contained modular units, or sheaves, within neural language models (LMs). Sheaves extend the concept of f…
cs.CL2024
What does the Knowledge Neuron Thesis Have to do with Knowledge?
Jingcheng Niu, Andrew Liu, Zining Zhu +1
We reassess the Knowledge Neuron (KN) Thesis: an interpretation of the mechanism underlying the ability of large language models to recall facts from a training corpus. This nascen…