App on FlowDot
The Transformer, Explained
An interactive visual explainer of the Transformer architecture and the "Attention Is All You Need" paper. Walk through tokenization, embeddings, live self-attention math (real QKV + softmax), multi-head attention, positional encoding, and the full encoder-decoder stack.
E
Elliot
Tags
education
ai
transformers
attention
interactive
deep-learning
nlp
The Transformer, Explained is an app on FlowDot by Elliot. Log out visitors see a sample of the author's output; log in to run it with your own inputs.
Sign up free to use this app and build your own.