Skip to content
Free public beta until December 4, 2026: every course is open, no card needed. After that, the first chapter of each course stays free and full access is a one-time $39 ($19 for up to 100 founding members chosen for helpful feedback). Your progress is kept. How the beta works

attention weight

A number indicating how strongly one position attends to another, produced by an attention mechanism's scoring step.

Examples

  • An attention weight of 0.75 on one key and 0.05 on another means the output leans heavily on the first value.

Read the full section →
Graph settings

Calculator