Towards Universality: Studying Mechanistic Similarity Across Language Model Architectures

The hypothesis of \textit{Universality} in interpretability suggests that different neural networks may converge toimplement similar algorithms on similar tasks. In this work, we investigate two mainstream architecturesfor language modeling, namely Transformers and Mambas, to explore the extent of their mechanistic similarity.We propose to use Sparse Autoencoders (SAEs) to isolate interpretable features from these models and showthat most features are similar in these two models. We also validate the correlation between feature similarityand~\univ. We then delve into the circuit-level analysis of Mamba modelsand find that the induction circuits in Mamba are structurally analogous to those in Transformers. We also identify a nuanced difference we call \emph{Off-by-One motif}: The information of one token is written into the SSM state in its next position. Whilst interaction between tokens in Transformers does not exhibit such trend.