Meet Tracr: DeepMind & ETH Zurich’s Novel Interpretability Tool Compiles Human-Readable Code to Transformers’ Weights | Synced

In the new paper Tracr: Compiled Transformers as a Laboratory for Interpretability, a research team from ETH Zurich and DeepMind presents Tracr, a compiler that addresses the absence of ground truth explanations in deep neural network models by “compiling” human readable code to the weights of a transformer model.