計測済みの棚AI・機械学習

Transformer explainers, ranked by where the analogy ends

水増しの中央値
36%
有用な部分の開始
1:36
典型的な尺
29 min

最終再計算 2026/9/16

Every video on this shelf has to solve the same problem: attention is a mechanism made of matrix multiplication, and matrix multiplication is not something you can watch. So each of them picks a metaphor — a lookup table, a search engine, a room where words vote on each other — and the entire quality of the video is decided by what happens after the metaphor.

The ones that rank highly here spend the metaphor quickly and then show the actual operation: what the three projections are, what shape the things being multiplied have, why the scaling term is there, what the mask does. The ones lower down keep the metaphor going for forty minutes, restated in progressively more elaborate ways, and never show a number.

Both types are titled “transformers explained”. The density measurement is what separates them, because a metaphor restated is by definition not new information, and it is the single most common way this topic becomes an hour of video.

Entries carry a difficulty level, and on this topic it matters more than anywhere else on the site: a video that is perfect for someone who already knows what a dot product does is a wasted hour for someone who does not, and the reverse is worse.

  1. 01

    Let's reproduce GPT-2 (124M)

    見る価値あり AndrejKarpathy 4:01:26 advanced

    密度
    84
    水増し
    27%
    有用な部分は
    3:34

    A code-complete, first-principles GPT-2 reproduction — one of the most valuable hands-on deep learning tutorials available.

    3:34から再生 →

  2. 02

    Attention in transformers, step-by-step | Deep Learning Chapter 6

    見る価値あり 3Blue1Brown 26:10 intermediate

    密度
    83
    水増し
    21%
    有用な部分は
    1:40

    A masterfully clear, dense walkthrough of the attention mechanism that rewards careful watching with real technical understanding.

    1:40から再生 →

  3. 03

    Transformers, the tech behind LLMs | Deep Learning Chapter 5

    見る価値あり 3Blue1Brown 27:14 intermediate

    密度
    80
    水増し
    26%
    有用な部分は
    1:26

    A masterclass primer on transformer internals — dense, rigorous, and exactly what its title promises.

    1:26から再生 →

  4. 04

    Let's build GPT: from scratch, in code, spelled out.

    流し見でOK AndrejKarpathy 1:56:20 advanced

    密度
    82
    水増し
    35%
    有用な部分は
    14:11

    A masterclass build-along: real working GPT code, the actual mechanics behind ChatGPT, with almost no filler.

    14:11から再生 →

  5. 05

    Transformer Neural Networks, ChatGPT's foundation, Clearly Explained!!!

    見る価値あり StatQuest with Josh Starmer 36:15 intermediate

    密度
    79
    水増し
    23%
    有用な部分は
    1:20

    A rigorous, worked-numbers walkthrough of transformer internals that actually teaches how ChatGPT-style models work, not just what they do.

    1:20から再生 →

  6. 06

    Large Language Models explained briefly

    見る価値あり 3Blue1Brown 7:58 intermediate

    密度
    75
    水増し
    26%
    有用な部分は
    0:33

    A masterfully compressed, accurate primer on how LLMs actually work — dense, honest, no sales pitch.

    0:33から再生 →

  7. 07

    Transformers Step-by-Step Explained (Attention Is All You Need)

    流し見でOK ByteByteGo 10:04 intermediate

    密度
    70
    水増し
    39%
    有用な部分は
    2:40

    A tight, genuinely educational explainer of Transformer attention with a real worked example, lightly interrupted by a disclosed sponsor read.

    2:40から再生 →

  8. 08

    Transformer Neural Networks - EXPLAINED! (Attention is all you need)

    見る価値あり CodeEmporium 13:05 intermediate

    密度
    68
    水増し
    31%
    有用な部分は
    1:54

    A dense, well-structured conceptual walkthrough of transformer architecture that earns its 'EXPLAINED' title with zero filler.

    1:54から再生 →

  9. 09

    Illustrated Guide to Transformers Neural Network: A step by step explanation

    見る価値あり The AI Hacker 15:01 intermediate

    密度
    72
    水増し
    31%
    有用な部分は
    1:03

    A tight, accurate conceptual tour of the Transformer's internals — solid teaching, though it retreads familiar illustrated-guide territory rather than breaking new ground.

    1:03から再生 →

  10. 10

    Transformers explained | The architecture behind LLMs

    見る価値あり AI Coffee Break with Letitia 19:48 intermediate

    密度
    71
    水増し
    33%
    有用な部分は
    0:38

    A genuinely dense, accurate transformer explainer that earns its title with real mechanics, not hype.

    0:38から再生 →

  11. 11

    Transformers: The best idea in AI | Andrej Karpathy and Lex Fridman

    流し見でOK Lex Clips 8:38 intermediate

    密度
    69
    水増し
    34%
    有用な部分は
    2:44

    A sharp, dense breakdown of why the Transformer works — one of the clearer plain-language explanations of its design philosophy, if brief.

    2:44から再生 →

  12. 12

    Transformers, explained: Understand the model behind GPT, BERT, and T5

    見る価値あり Google Cloud Tech 9:11 intermediate

    密度
    67
    水増し
    34%
    有用な部分は
    1:25

    A genuinely solid, jargon-light explainer of transformer architecture that earns its title without ever really selling anything.

    1:25から再生 →

  13. 13

    Transformers for beginners | What are they and how do they work

    見る価値あり AssemblyAI 19:59 beginner

    密度
    68
    水増し
    29%
    有用な部分は
    0:31

    Solid, math-grounded beginner explainer of transformer internals, lightly bookended by the channel's own API plug.

    0:31から再生 →

  14. 14

    Transformers Explained | Simple Explanation of Transformers

    見る価値あり codebasics 57:31 intermediate

    密度
    67
    水増し
    27%
    有用な部分は
    1:36

    A patient, analogy-heavy but genuinely thorough walkthrough of Transformer internals — worth the long runtime if you already know your deep learning basics.

    1:36から再生 →

  15. 15

    How does AI actually work? Transformers explained

    見る価値あり AI Search 32:21 intermediate

    密度
    66
    水増し
    30%
    有用な部分は
    0:31

    A solid, honestly-titled conceptual explainer of Transformer architecture, weakened only by redundant recaps and a mid-video sponsor detour.

    0:31から再生 →

  16. 16

    Transformer Architecture Explained 'Attention Is All You Need'

    見る価値あり ByteMonk 12:49 intermediate

    密度
    62
    水増し
    34%
    有用な部分は
    0:47

    A clear, well-paced conceptual primer on Transformer attention — not groundbreaking, but a genuinely solid explainer worth the 13 minutes for newcomers to the architecture.

    0:47から再生 →

  17. 17

    Transformers, explained: Understand the model behind ChatGPT

    流し見でOK Leon Petrou 24:07 beginner

    密度
    61
    水増し
    28%
    有用な部分は
    3:29

    A clear, accessible mental model of how Transformers work end-to-end — skips the real attention math (no Q/K/V) but is genuinely useful as a conceptual primer.

    3:29から再生 →

  18. 18

    What are Large Language Models (LLMs)?

    流し見でOK Google for Developers 5:30 beginner

    密度
    56
    水増し
    41%
    有用な部分は
    0:32

    A tight, honest beginner explainer of LLMs and prompt design — light on depth but dense and accurate for its length.

    0:32から再生 →

  19. 19

    Everything You Need To Know About Large Language Models (LLMs)

    流し見でOK Matthew Berman 25:20 beginner

    密度
    58
    水増し
    39%
    有用な部分は
    0:32

    A solid, broad beginner's overview of LLM mechanics and history, only lightly diluted by a sponsor segment for AI Camp.

    0:32から再生 →

  20. 20

    The Transformer architecture

    流し見でOK Hugging Face 2:45 beginner

    密度
    50
    水増し
    47%
    有用な部分は
    0:59

    A clean, honest, high-level primer that sets up the series without pretending to teach the deep mechanics yet.

    0:59から再生 →

  21. 21

    What are Transformers (Machine Learning Model)?

    流し見でOK IBM Technology 5:51 beginner

    密度
    51
    水増し
    46%
    有用な部分は
    1:17

    A clear, accurate but fairly standard conceptual primer on transformers — solid intro, low novelty.

    1:17から再生 →

  22. 22

    Transformer Explained

    流し見でOK Caleb Writes Code 6:55 intermediate

    密度
    55
    水増し
    40%
    有用な部分は
    2:07

    A solid conceptual primer on transformer limitations and fixes, but it openly admits it skips the actual mechanics the title implies.

    2:07から再生 →

  23. 23

    Large Language Models Explained Simply (In 13 Minutes)

    流し見でOK The Gradient Descent 12:57 beginner

    密度
    50
    水増し
    45%
    有用な部分は
    3:21

    A clear, if conceptually shallow, LLM 101 explainer padded with light jokes and capped by a short affiliate plug.

    3:21から再生 →

  24. 24

    Large Language Models | How Large Language Models Work? | Introduction to LLM | Simplilearn

    流し見でOK Simplilearn 15:47 beginner

    密度
    46
    水増し
    48%
    有用な部分は
    2:46

    A solid, if generic, beginner overview of how LLMs and transformers work, padded with a short in-house course pitch.

    2:46から再生 →

  25. 25

    How Large Language Models Work

    スキップ IBM Technology 5:34 beginner

    密度
    48
    水増し
    51%
    有用な部分は
    2:04

    A clear, competent beginner overview of LLM mechanics from IBM, though fairly generic and light on real depth.

    2:04から再生 →

Gistil's own measurement. Not a YouTube rating, and not the channel's position. 順位は私たちのものですが、動画自体はそれぞれのチャンネルに属します。

この順位はどう決まるのか

ここにあるすべての動画は同じ軸で計測されています——尺のどれだけが情報を運んでいるか、どれだけが水増しか、そして何秒から元が取れ始めるか。並び順は価値密度によるもので、再生回数や新しさ、私たちのチャンネルへの好みによるものではありません。数字が意味するもの →

← ai・機械学習の計測済み動画すべて