Gurnee and Tegmark (2023) demonstrated that Large Language Models learn linear representations for spatial and temporal dimensions, which allows the models to map geography and history across multiple scales.

Authors

• Person: Not available Organization: arXiv
  A Survey on the Theory and Mechanism of Large Language Models

Sources

• A Survey on the Theory and Mechanism of Large Language Models arxiv.org arXiv via serper

Referenced by nodes (2)

• Large Language Models concept
• history concept