Thanks to KiwiCo for sponsoring today's video! Go to https://www.kiwico.com/welchlabs and use code WELCHLABS for 50% off your first month of monthly lines and/or for 20% off your first Panda Crate.

Activation Atlas Posters!
https://www.welchlabs.com/resources/5...
https://www.welchlabs.com/resources/a...
https://www.welchlabs.com/resources/l...
https://www.welchlabs.com/resources/a...

Special thanks to the Patrons:
Juan Benet, Ross Hanson, Yan Babitski, AJ Englehardt, Alvin Khaled, Eduardo Barraza, Hitoshi Yamauchi, Jaewon Jung, Mrgoodlight, Shinichi Hayashi, Sid Sarasvati, Dominic Beaumont, Shannon Prater, Ubiquity Ventures, Matias Forti

Welch Labs
Ad free videos and exclusive perks:   / welchlabs  
Watch on TikTok:   / welchlabs  
Learn More or Contact: https://www.welchlabs.com/
Instagram:   / welchlabs  
X:   / welchlabs  

References
AlexNet Paper
https://proceedings.neurips.cc/paper_...

Original Activation Atlas Article explore here Great interactive Atlas! https://distill.pub/2019/activationa...
Carter, et al., "Activation Atlas", Distill, 2019.

Feature Visualization Article: https://distill.pub/2017/featurevisu...
`Olah, et al., "Feature Visualization", Distill, 2017.`

Great LLM Explainability work: https://transformercircuits.pub/2024...
Templeton, et al., "Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet", Transformer Circuits Thread, 2024.

“Deep Visualization Toolbox" by Jason Yosinski video inspired many visuals:
   • Deep Visualization Toolbox  

Great LLM/GPT Intro paper
https://arxiv.org/pdf/2304.10557

3B1Bs GPT Videos are excellent, as always:
   • Attention in transformers, visually e...  
   • But what is a GPT?  Visual intro to t...  

Andrej Kerpathy's walkthrough is amazing:
   • Let's build GPT: from scratch, in cod...  

Goodfellow’s Deep Learning Book
https://www.deeplearningbook.org/

OpenAI’s 10,000 V100 GPU cluster (1+ exaflop) https://news.microsoft.com/source/fea...

GPT3 size, etc: Language Models are FewShot Learners, Brown et al, 2020.

Unique token count for ChatGPT: https://cookbook.openai.com/examples/...

GPT4 training size etc, speculative:
https://patmcguinness.substack.com/p/...
https://www.semianalysis.com/p/gpt4...

Historical Neural Network Videos
   • Convolutional Network Demo from 1989  
   • Perceptron Research from the 50's & 6...