"linear representations" Papers
4 papers found
Conference
Attention layers provably solve single-location regression
Pierre Marion, Raphaël Berthier, Gérard Biau et al.
ICLR 2025arXiv:2410.01537
11
citations
On Linear Representations and Pretraining Data Frequency in Language Models
Jack Merullo, Noah Smith, Sarah Wiegreffe et al.
ICLR 2025arXiv:2504.12459
11
citations
Exploring the LLM Journey from Cognition to Expression with Linear Representations
Yuzi Yan, Jialian Li, YipinZhang et al.
ICML 2024arXiv:2405.16964
6
citations
On the Origins of Linear Representations in Large Language Models
Yibo Jiang, Goutham Rajendran, Pradeep Ravikumar et al.
ICML 2024arXiv:2403.03867
58
citations