Mechanistic interpretability of Zamba2-1.2B hybrid SSM — SSMI, copy scores, logit-lens factual recall. First analysis of weight-tied attention in hybrid architectures.
-
Updated
Jul 6, 2026 - Jupyter Notebook
Mechanistic interpretability of Zamba2-1.2B hybrid SSM — SSMI, copy scores, logit-lens factual recall. First analysis of weight-tied attention in hybrid architectures.
To associate your repository with the zamba2 topic, visit your repo's landing page and select "manage topics."