How neural networks bend space

This is the first of a trilogy of videos titled "The world's smallest transformer model". In this video, we study how LLMs bend space in order to classify data. We start with an image recognition example, but we move to a neural network that talks by generating the next word in a sentence. Video 1: How neural networks bend space (this one) Video 2: The world's smallest transformer model https://www.youtube.com/watch?v=3ZxbaeqZIHQ Video 3: The world's smallest attention mechanism https://www.youtube.com/watch?v=J4hSc9He614 ADDENDUM: Key and Query Matrices worked out in detail https://www.yout