Dontopedia

SiLU

From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-06.)

SiLU has 12 facts recorded in Dontopedia across 5 references, with 1 live disagreement.

12 facts·9 predicates·5 sources·1 in dispute

Mostly:rdf:type(2), has op count per ffn forward pass(1), defined by parameters(1)

Maturity scale raw canonical shape-checked rule-derived certified

Inbound mentions (4)

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)

hasSpecialCaseHas Special Case(1)

startsAsStarts As(1)

usesActivationUses Activation(1)

Other facts (10)

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.

10 facts
PredicateValueRef
Rdf:typeActivation Function[3]
Rdf:typeActivation Function[5]
Has Op Count Per Ffn Forward Pass3[1]
Defined by Parameters{"α": 1, "β": 0}[2]
Learnable Param Count0[3]
NoteStandard smooth[3]
StatusWinning Parent[4]
Predicted LikelihoodMost Likely Winner[4]
Advantage TypeStructural Advantage[4]
Acronym ofSigmoid Linear Unit[5]

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.

12 undated
—
hasOpCountPerFfnForwardPassblah/training-and-evals/part-28
3
—
labelblah/training-and-evals/20
SiLU
—
definedByParametersblah/training-and-evals/20
{"α": 1, "β": 0}
—
typeblah/training-and-evals/23
ex:ActivationFunction
—
labelblah/training-and-evals/23
silu
—
learnableParamCountblah/training-and-evals/23
0
—
noteblah/training-and-evals/23
Standard smooth
—
statusblah/training-and-evals/24
ex:winning-parent
—
predictedLikelihoodblah/training-and-evals/24
ex:most-likely-winner
—
advantageTypeblah/training-and-evals/24
ex:structural-advantage
—
typeblah/watt-activation/509
ex:ActivationFunction
—
acronymOfblah/watt-activation/509
Sigmoid Linear Unit

References (5)

5 references
  1. [1]Part 281 fact
    ctx:discord/blah/training-and-evals/part-28
  2. [2]202 facts
    ctx:discord/blah/training-and-evals/20
    • full texttraining-and-evals-20
      text/plain3 KBdoc:agent/training-and-evals-20/df884008-3d53-4aea-97bd-68748c59313f
      Show excerpt
      [2026-02-25 10:19] ajaxdavis: ``` There are a few concrete approaches, from least to most ambitious: 1. Parameterized activations (easy, high value) Instead of choosing between gelu and silu, parameterize a family that contains both a…
  3. [3]234 facts
    ctx:discord/blah/training-and-evals/23
    • full texttraining-and-evals-23
      text/plain3 KBdoc:agent/training-and-evals-23/70bec41a-b6db-4999-9455-15d7176b4205
      Show 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…
  4. [4]243 facts
    ctx:discord/blah/training-and-evals/24
    • full texttraining-and-evals-24
      text/plain2 KBdoc:agent/training-and-evals-24/b280a4e7-48a7-4bc2-9593-e4261e806744
      Show 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…
  5. [5]5092 facts
    ctx:discord/blah/watt-activation/509
    • full textwatt-activation-509
      text/plain3 KBdoc:agent/watt-activation-509/ac112e0d-7c5e-462b-98e5-9734c2773399
      Show excerpt
      [2026-03-22 20:48] xenonfun: ⏺ CHON RUL results: ``` ┌─────────────┬───────────────────┬───────────────────────────────────┐ │ Metric │ Value │ Notes │ ├─────────────┼───────────────────┼──…

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.

↑