Deep Visualization Toolbox

Highly recommend this video on the Deep Visualization Toolbox to anyone interesting in understanding more about how convnets work through visualization: link to this video

This toolbox allows you to visualize what neural networks "see" at each layer, and what image patterns activate what sorts of neurons (and how). For example, in this video 1 you can see neurons that detect edges, faces, and text. 1 link to this video

And it also suffers from the tired assumption that GPT-3 (or any language models) should, or are designed to in any way, give reasonable answers1. All GPT-3 does is give likely continuations , given the training corpus. The prompts here are too short, and it could likely just be writing mediocre fiction continuations. Fiction tends to not be reasonable much of the time (to create story conflict). > "To understand why, it helps to think about what systems like GPT-3 do. They don’t learn about the world—they learn about text and how people use words in relation to other words. What it does is something like a massive act of cutting and pasting, stitching variations on text that it has seen,…

Why not? It takes models of a certain size to contain xyz neuron/feature. link to this video That's not a mirage, it's clearly capability that a smaller model cannot demonstrate. A model with less parameters and less hidden layers cannot have a neuron that lights up when it detects a face.