Track 4 · Path · 6 explainers
How LLMs Work
From attention to decoder-only transformers, the architecture behind GPT
- 1
How Self-Attention Works
Query, key, value — the core of self-attention
- 2
Multi-Head Attention
Parallel attention heads learning different patterns
- 3
Positional Encoding
How transformers know word order
- 4
Cross-Attention
Attending across sequences and modalities
- 5
The Transformer Architecture
A visual guide to 'Attention Is All You Need'
- 6
Decoder-Only Transformers
The architecture behind GPT and modern LLMs