Apperently it’s more efficient to do it other way around, to compile programs into transformers, which are then useful as refecene and ground truth when analyzing “real” transformers.
See usage of TRACR in “Towards Automated Circuit Discovery for Mechanistic Interpretability” https://arxiv.org/pdf/2304.14997, for example.
Apperently it’s more efficient to do it other way around, to compile programs into transformers, which are then useful as refecene and ground truth when analyzing “real” transformers.
See usage of TRACR in “Towards Automated Circuit Discovery for Mechanistic Interpretability” https://arxiv.org/pdf/2304.14997, for example.