Transformer Studio

Visual scaled dot-product attention, multi-head projection & next-token sampling

Live Transformer Lab
1. Multi-Head Self-Attention Heatmap (Q × Kᵀ / √dₖ) Click cell to inspect math
2. Live Attention Inspector
Select any token or matrix cell to trace calculations.
Query (Q): -
[--]
Key (K): -
[--]
3. Next-Token Output Distribution