You can have a transformer based index built on top of a graph database. Much of the explainability tech (people who prefer "alignment" also prefer "mechanistic interpretability") is reverse engineering the real world graph that's hiding in the weights.

https://research.google/pubs/the-case-for-learned-index-stru...

That's literally not useful for the sort of applications people want to use transformers for.

What you're using is a transformer based database index. An obfuscated one.

Training data is the database. Model is a lossy compressed index.