Tag
This paper re-derives activation patching from causal mediation analysis, revealing that the natural indirect effect (NIE) captures not only a component's causal effect but also interaction effects with other components. It demonstrates these hidden interactions in the GPT-2 IOI circuit and argues that they are a diagnostic tool rather than a nuisance.
This paper introduces the readout-mediator angle to demonstrate that linear probes can decode information from language model activations that is orthogonal to the model's actual causal computation, undermining probe-based interpretability. The finding replicates across model scales and families, revealing a fundamental failure mode in using probes for mechanistic understanding or safety monitoring.