A Mathematical Framework for Transformer Circuits (opens in new tab)

Transformer language models are an emerging technology that is gaining increasingly broad real-world use, for example in systems like GPT-3 , LaMDA , Codex , Meena , Gopher , and similar models.  However, as these models scale, their open-endedness and high capacity creates an increasing scope for unexpected and sometimes harmful behaviors.  Even years after a large model is trained, both creators and users routinely discover model capabilities – including problematic behaviors – they were pr...