Shows the practical moves of mechanistic interpretability — reading weight matrices directly, working backward from the final layers — on a network deliberately built so that backpropagating from the output tells you nothing.

• articleUnderstanding LLM Architectures WorkflowSebastian Raschka, PhD
• clipWhy you can delete 86% of a model's weights without breaking itAI Engineer
• repoNeural Networks: Zero to HeroAndrej Karpathy

Checking sign-in…

Loading comments…