//
attention
STEP 01
Why Attention?
⏸ Pause
⏭ Step
↺ Reset
Speed
0.5×
🌙
01 · Why Attention
›
02 · Q K V Vectors
›
03 · Q·Kᵀ Scores
›
04 · Scale + Softmax
›
05 · Attention Heatmap
›
06 · V Weighted Sum
›
07 · Multi-Head
›
08 · Full Pass
STEP 01 · WHY ATTENTION?
Starting attention mechanism…
// STEP 01 · WHY ATTENTION?
Every token looks at every other token.
Attention solves the long-range dependency problem.
This page
0:00
This session
0:00
Total (all pages)
0:00
Today
0:00
▶ Running
📊 View all study stats →
0:00
studying