LIT and PCA

Let's start off by running the intuitive LIT tool.

Overview of LIT

LIT’s visual interface will help us find examples that the model processes incorrectly, dig into similar examples, see how the model behaves when we change a context, and more language issues related to transformer models.

LIT does not display the activities of the attention heads like BertViz does. However, it’s worth analyzing why things went wrong and trying to find solutions.

We can choose a Uniform Manifold Approximation and Projection (UMAP) visualization or a PCA projector representation. PCA will make more linear projections in specific directions and magnitude. UMAP will break its projections down into mini-clusters. Both approaches make sense depending on how far we want to go when analyzing the output of a model. We can run both and obtain different perspectives of the same model and examples.

This lesson will use PCA to run LIT. Let’s begin with a brief reminder of how PCA works.

Overview of PCA

PCA takes data and represents it at a higher level. Imagine you are in your kitchen. Your kitchen is a 3D cartesian coordinate system. The objects in your kitchen are all at specific x, y, z coordinates too.
You want to cook a recipe and gather the ingredients on your kitchen table. Your kitchen table is a higher-level representation of the recipe in your kitchen.