THE CONNECTED RECORD
Ask
the work.
Find the film. Read the words. Return to the source.
241 FILMS · 2 TIMED TRANSCRIPTS · SOURCE SEARCH
Search the house’s own description and its source records. This first edition retrieves material rather than generating an answer. Automatic captions are unreviewed. Films without indexed captions can be found by their titles and available descriptions. Browse the complete catalogue for draft questions and notebook entries, which are not treated as published evidence here.
3 RESULTS FOR “ffn”
AUTOMATIC CAPTIONS / 7:26
LLMs Are Databases - So Query Them ↗
geographic neighbors as well. So, let's go a little bit raw here. That was a pretty clean view. Let's look at the feedforward network underneath the hood there. Again, everything we're looking at is the FFN, which is really the knowledge store where all of the data stored. Attention is slightly different. We'll talk about that later. But if I do something like show features, and again we'll limit it to layer 26. Feature two is really
ORIGINAL SOURCE ↗AUTOMATIC CAPTIONS / 8:44
LLMs Are Databases - So Query Them ↗
stores that within the weight? So, basically, a feature is a single column in the FFN. It's one gate vector that decides when it fires, and one down vector that decides what it outputs. Gate times down. That is basically the edge. So, it's an edge in the graph. And the gate is a direction in the residual stream. I'm not going to go into too much detail of what a residual stream is. I've
ORIGINAL SOURCE ↗TITLE & DESCRIPTION
LLMs Are Databases - So Query Them ↗
What if the FFN weights in a transformer aren't a black box — but a graph database you can query directly?
ORIGINAL SOURCE ↗