mechanistic-interpretability
4 free lessons tagged mechanistic-interpretability across AI. Each one is a short sequence of focused steps with narration and a five-question quiz at the end — take them in any order, no signup required.
Causal Interventions, Steering, and What Remains Open
Turning interpretability stories into tested claims: activation patching, model editing, steering vectors, the attribution graphs that trace circuits in production models, and the problems the field has not solved.
Sparse Autoencoders and Dictionary Learning
How an unsupervised model trained on activations pulls features back out of superposition, what it found when scaled to a production language model, and where the method still breaks down.
Circuits: Reverse-Engineering Transformer Algorithms
How attention heads read and write to a shared residual stream, how they compose into circuits, and the two best-understood examples: the induction head behind in-context learning and the indirect object identification circuit in GPT-2.
Features, Directions, and Superposition
Why individual neurons are the wrong unit for understanding a neural network, and what the superposition hypothesis says is really going on inside the activations.