Open-sourcing circuit-tracing tools

In our recent interpretability research, we introduced a new method to trace the thoughts of a large language model. Today, we’re open-sourcing the method so that anyone can build on our research. Our approach is to generate attribution graphs, which (partially) reveal the steps a model took internally to decide on a particular output. The open-source library we’re releasing supports the generatio

[misshiki]

“最近の解釈可能性研究において、大規模言語モデルの思考をトレースする新しい手法を導入しました。本日、この手法をオープンソース化し、誰でも私たちの研究を発展させることができるようにします。”