Concept · Building with AI

Interpretability

Also called: mechanistic interpretability, explainability, explainable AI, XAI

Research into what is happening inside an AI model: which internal patterns represent which ideas and how they lead to an output.

For example: Interpretability researchers find a pattern inside a model that switches on whenever the text mentions a particular city.

Connects to 4

• Neural network Concept
• Latent space Concept
• AI safety Concept
• Alignment Concept