---
# edu-vqxk
title: 'Write §8: A decoder-only LM — stacking blocks and the causal mask'
status: completed
type: task
priority: normal
created_at: 2026-03-13T22:01:58Z
updated_at: 2026-03-16T02:30:26Z
parent: edu-u2w7
---

Explain how N transformer blocks are stacked. Causal mask ensures each position only attends to past tokens. Tie weights to the unembedding matrix (GPT-1 style). Final linear + softmax for logits.