An Adversarial Example for Direct Logit Attribution: Memory Management in gelu-4l

We provide concrete evidence for memory management in a 4-layer transformer. Specifically, we identify clean-up behavior, in which model components consistently remove the output of preceeding components during a forward pass. Our findings suggest that the interpretability technique Direct Logit Attribution provides misleading results. We show explicit examples where this technique is inaccurate, as it does not account for clean-up behavior.