← Back to Labs

LLM Attention Weights

See tokenisation, attention scoring, weighted value mixing, and KV cache reuse through one short prompt.

Context WindowSofiaopenedthe archivebecause she needed the log55%20%15%10%
Step 1 / 4Tokenisation creates fixed vocabulary IDs

The model sees token pieces, not whole human ideas. Even a short sentence becomes a sequence of learned token IDs.

Arrow keys to navigate · R to reset

Tap dots to jump to any step

Read the full article →Take the quiz →