j⧉nus @repligate · 11 Sep 2025
HOW INFORMATION FLOWS THROUGH TRANSFORMERS Because I've looked at those "transformers explained" pages and they really suck at explaining. There are two distinct information highways in the transformer architecture: - The residual stream (black arrows): Flows vertically through https://t.co/IVsNUq4hUT
947 080Views
3 536Likes
436Reposts
113Replies
93Quotes
4 991Bookmarks
Is that a lot?
192×vs this author's median4 944 views is typical
100Percentile for this authorof 6 recent posts
510×vs 10K–100K median1 856 views is typical
13.9× audienceReachviews ÷ followers
0.44%Engagement rateof viewers reacted