Inner Interpretability is a promising emerging field tasked with uncovering the inner mechanisms of AI systems, though how to develop these mechanistic theories is still much debated. Moreover, recent critiques raise issues that question its usefulness to advance the broader goals of AI. However, it has been overlooked that these issues resemble those that have been grappled with in another field: Cognitive Neuroscience. Here we draw the relevant connections and highlight lessons that can be transferred productively between fields. Based on these, we propose a general conceptual framework and give concrete methodological strategies for building mechanistic explanations in AI inner interpretability research. With this conceptual framework, Inner Interpretability can fend off critiques and position itself on a productive path to explain AI systems.

Machine learning is currently involved in some of the most vigorous debates it has ever seen. Such debates often seem to go around in circles, reaching no conclusion or resolution. This is perhaps unsurprising given that researchers in machine learning come to these discussions with very different frames of reference, making it challenging for them to align perspectives and find common ground. As a remedy for this dilemma, we advocate for the adoption of a common conceptual framework which can be used to understand, analyze, and discuss research. We present one such framework which is popular in cognitive science and neuroscience and which we believe has great utility in machine learning as well: Marr's levels of analysis. Through a series of case studies, we demonstrate how the levels facilitate an understanding and dissection of several methods from machine learning. By adopting the levels of analysis in one's own work, we argue that researchers can be better equipped to engage in the debates necessary to drive forward progress in our field.

Multi-representational architectures exploit diversity to yield the breadth of capabilities required for intelligent behavior in the world, but in so doing can sacrifice too much of the complementary benefits of architectural uniformity. The proposal here is to couple the benefits of diversity and uniformity through establishment of a uniform graph-based implementation level for diverse architectures.