To understand neural network behavior, recent works quantitatively compare different networks' learned representations using canonical correlation analysis (CCA), centered kernel alignment (CKA), and other dissimilarity measures. Unfortunately, these widely used measures often disagree on fundamental observations, such as whether deep networks differing only in random initialization learn similar representations. These disagreements raise the question: which, if any, of these dissimilarity measures should we believe? We provide a framework to ground this question through a concrete test: measures should have \emph{sensitivity} to changes that affect functional behavior, and \emph{specificity} against changes that do not. We quantify this through a variety of functional behaviors including probing accuracy and robustness to distribution shift, and examine changes such as varying random initialization and deleting principal components.

To understand neural networks, researchers often use similarity metrics to measure how similar or different two neural networks are to each other. For instance, they are used to compare vision transformers to convnets [1], to understand transfer learning [2], and to explain the success of standard training practices for deep models [3]. CKA (Centered Kernel Alignment) similarity between two networks trained identically except for random initialization. Lower values (darker colors) are more similar. CKA suggests that the two networks have similar representations.