podcasts / The attention family / episode / question
Question

How does a key weight matrix change attention scores in Vizuara's dog and ball example?

Answered from Q, K, V intuition - self attention with trainable weights | The attention family series - Lecture 6 · The attention family · 2026-09-18

Sreedath Panat gives it, dog and ball toy three-dimensional embeddings of (0.5, 0.5, 0.1), (0.9, 0.1, 0.1) and (0.1, 0.9, 0.1). Raw dot products give it 0.51 against both nouns. He then passes only the keys through a diagonal W_K matrix with entries 1, 2 and 1: dog becomes (0.9, 0.2, 0.1) and ball becomes (0.1, 1.8, 0.1). Now it scores 0.56 against dog and 0.96 against ball, so it attends more to ball, as the sentence requires.

Source: our own transcription of the episode. The full conversation is on The attention family (2026-09-18). Read the whole episode summary →

▸More from this episode

Q1What do query, key and value mean in self-attention, according to Vizuara?Q2Why can't self-attention use raw input embeddings for attention scores?Q4What does an attention-weighted sum of value vectors mean in the transformer formula?Q5Can the query, key and value space have a different dimension from the input embeddings?Q6How are the W_Q, W_K and W_V weight matrices learned in an LLM?
Transcribe your links. Paste a YouTube, Google Drive or podcast link and WhipScribe gives you the transcript. Transcribe a link →