Attention in transformers, step-by-step | Deep Learning Chapter 6
What it is
3Blue1Brown's visual walkthrough of the attention mechanism inside transformers, covering self-attention, multiple heads and cross-attention. It is chapter 6 of his deep learning series.
Why Hacker News recommends it
HN treats it as the go-to visual explanation of attention, recommended to people who find text-based transformer explainers hard to follow.
- 5 people recommended it
- 4 different months
- 2 strong recommendations
- first 2024, last 2026
What HN commenters said
“what bade me finally understand the transformer architecture [0] and attention [1], are 3Blue1Brown's videos.”
Made the commenter finally understand transformers and attention.
tomashm, 2024-07 · Strong recommendation · in “The Illustrated Transformer (2018)”
“If you aren't familiar with hyper words, this is an amazing series”
Amazing series on how tokens become vectors and mutate through attention.
onlyrealcuzzo, 2026-05 · Strong recommendation · in “Claude Opus 4.8”
“Attention in transformers, visually explained | Chapter 6, Deep Learning”
Visual explanation of attention in a list of better resources.
MAXPOOL, 2024-07 · Recommendation · in “The Engineer’s Guide to Deep Learning: Understanding the Transformer Model”
“I suggest checking out 3blue1brown's videos on gradient descent”
Shows how attention actually works, versus voting metaphor.
superkuh, 2024-10 · Recommendation · in “LLMs Aren't Thinking, They're Just Counting Votes”
“For something gentler, 3Blue1Brown”
Gentler introduction to attention, part of a series.
wren6991, 2026-06 · Recommendation · in “Can I Buy Your KV Cache?”
Excerpts from Hacker News comments, linked to the originals. Summaries and labels were written by a language model from those comments.
Topics: attention, transformers, llm, deep learning, visualization, 3blue1brown
Also recommended by the same people
explainerTransformers, the tech behind LLMs | Deep Learning Chapter 53Blue1Brown · 13 HN recommenders · 2024–2026
talkAre We There Yet - Rich HickeyZhang Jian · 4 HN recommenders · 2021–2026
explainerBut what is a neural network? | Deep learning chapter 13Blue1Brown · 16 HN recommenders · 2017–2025
explainerBut what is the Fourier Transform? A visual introduction.3Blue1Brown · 16 HN recommenders · 2018–2025
explainerGradient descent, how neural networks learn | Deep Learning Chapter 23Blue1Brown · 4 HN recommenders · 2017–2024
explainerHow does Computer Memory Work? 💻🛠Branch Education · 5 HN recommenders · 2022–2023
lectureAT&T Archives: Similiarities of Wave Behavior (Bonus Edition)AT&T Tech Channel · 12 HN recommenders · 2014–2026
lectureDeep Dive into LLMs like ChatGPTAndrej Karpathy · 10 HN recommenders · 2025–2026