Interactive explainer connecting Sparse Non-Negative Activations to Pathway's BDH - DataForge 2026, Pathway Track
-
Updated
Sep 10, 2026 - HTML
#
sparse-activations
Here are 3 public repositories matching this topic...
Interactive explainer: BDH's attention has no softmax, so it is exactly a Hebbian synaptic memory — one fixed-size matrix written once per token. Run both forms, watch them agree to 1e-16, then break it with one toggle. DataForge 2026, Pathway track.
machine-learning attention-mechanism hebbian-learning associative-memory pathway fast-weights interpretability explorable-explanations neurips linear-attention bdh dragon-hatchling interactive-explainer post-transformer sparse-activations
-
Updated
Sep 8, 2026 - HTML
A 397k-parameter Dragon Hatchling runs in your browser. It quietens on text it just learned, not on text that is merely predictable. DataForge 2026, Pathway Track.
-
Updated
Sep 8, 2026 - HTML
Add this topic to your repo
To associate your repository with the sparse-activations topic, visit your repo's landing page and select "manage topics."