swiglu
From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-06.)
swiglu has 15 facts recorded in Dontopedia across 3 references, with 2 live disagreements.
Mostly:involves operations(5), rdf:type(1), learnable param count(1)
Maturity scale
raw canonical shape-checked rule-derived certifiedInbound mentions (1)
Other subjects in dontopedia point AT this entity as a value. These are inverse relationships — e.g. "X motherOf this subject" — and answer questions the forward facts can't. Grouped by predicate.
activationCompetitorActivation Competitor(1)
- Super Chat 20260225143238 Sa7h
ex:super-chat-20260225143238-sa7h
Other facts (13)
The long tail: predicates that appear too rarely to warrant their own section. Filter or scroll to find a specific one. Each row links to its source.
| Predicate | Value | Ref |
|---|---|---|
| Involves Operations | Matmul Gate | [3] |
| Involves Operations | Silu | [3] |
| Involves Operations | Matmul Up | [3] |
| Involves Operations | Mul | [3] |
| Involves Operations | Matmul Proj | [3] |
| Rdf:type | Activation Function | [1] |
| Learnable Param Count | 0 | [1] |
| Note | Gated architecture | [1] |
| Predicted Likelihood | Most Likely Winner | [2] |
| Advantage Type | Structural Advantage | [2] |
| Advantage Context | Low Step Counts | [2] |
| Has Op Count | 5 | [3] |
| Has Parametric Difference | 50% more params | [3] |
Timeline
Timeline axis is valid_time — when each source says the fact was true in the world, not when Dontopedia learned about it. Retracted rows are kept for provenance; coloured stripes indicate the context kind.
References (3)
ctx:discord/blah/training-and-evals/23- full texttraining-and-evals-23text/plain3 KB
doc:agent/training-and-evals-23/70bec41a-b6db-4999-9455-15d7176b4205Show excerpt
[2026-02-25 14:27] omega [bot]: **Symbio Search Math Problem** Current run `super_chat_20260225140824_ee4k` has a config mismatch: ``` 50000 candidates × 3000 steps × 20 gens = 3,000,000,000 total search steps But only 50,000 total trainin…
ctx:discord/blah/training-and-evals/24- full texttraining-and-evals-24text/plain2 KB
doc:agent/training-and-evals-24/b280a4e7-48a7-4bc2-9593-e4261e806744Show excerpt
[2026-02-25 14:46] omega [bot]: **Selective Pressure — Three Mechanisms** **1. Evaluation Pressure** (per-candidate) Each candidate gets exactly 30 steps to prove itself. Records bestLoss, bestValLoss, fitnessScore. At 30 steps during warm…
ctx:discord/blah/training-and-evals/28- full texttraining-and-evals-28text/plain3 KB
doc:agent/training-and-evals-28/d5fb7857-3e3e-4219-8c84-377b4bfc1defShow excerpt
[2026-02-25 15:46] omega [bot]: **When Do Universal & KAN Spline Get Faster?** Short answer: **they don't get faster.** Their tok/s is fixed by their op count. But here's the full picture. **Op count per FFN forward pass (per layer × 8 la…
See also
Keep researching
Missing something or suspicious of what's here? Kick off a research session — a Claude agent will investigate, cite its sources, and file new facts into a dedicated context you can review before accepting into the shared view.