The glossary
Every word you'll meet in AI and machine learning, explained in everyday language.
What an attention head writes once it has looked at a token, as one table made by multiplying its value and output matrices with the embedding and the output layer.
Five tensors of the copying model. The bars at the bottom are the singular values, largest first, and the sentence above them says how many hold 90% of the energy.
Reading weights without running the model · Singular values, and an attention head's token-to-token circuit, read from the matrices alone and then checked against a measurement. About 35 minutes.
1286 terms in the glossary, each with the lesson that teaches it.
Every word you'll meet in AI and machine learning, explained in everyday language.
Singular values, and an attention head's token-to-token circuit, read from the matrices alone and then checked against a measurement.
Never trained an AI? Teach a small one to write, right in your browser. It takes about 20 seconds and needs no account. Teach it to write