The Linear Representation Hypothesis (LRH) posits that high-level semantic concepts are encoded as linear directions within the activation space of Large Language Models.

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 (1)

• Large Language Models concept