Dontopedia

pos_emb

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

pos_emb has 9 facts recorded in Dontopedia across 4 references.

9 facts·8 predicates·4 sources

Mostly:limits quality(1), supports up to(1), constitutes percent of total(1)

Maturity scale raw canonical shape-checked rule-derived certified

Inbound mentions (2)

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.

secondaryToPosEmbSecondary to Pos Emb(1)

sumIncludesSum Includes(1)

Other facts (8)

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.

8 facts
PredicateValueRef
Limits QualityContext Length[1]
Supports Up to2048[2]
Constitutes Percent of Total87.23[3]
Implicates High Param Cost for Long Seq131072 Seq[3]
Essential for Long Seq LenMax Seq Len 131072[3]
Has Num Params109051904[3]
Rdf:typeModel Component[4]
Supports Max Sequence Length2048[4]

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.

limitsQualityblah/watt-activation/part-126
ex:context-length
supportsUpToblah/watt-activation/part-125
ex:2048
constitutesPercentOfTotalblah/watt-activation/part-263
87.23
implicatesHighParamCostForLongSeqblah/watt-activation/part-263
ex:131072-seq
essentialForLongSeqLenblah/watt-activation/part-263
ex:max-seq-len-131072
hasNumParamsblah/watt-activation/part-263
109051904
typeblah/watt-activation/125
ex:ModelComponent
labelblah/watt-activation/125
pos_emb
supportsMaxSequenceLengthblah/watt-activation/125
2048

References (4)

4 references
  1. [1]Part 1261 fact
    ctx:discord/blah/watt-activation/part-126
  2. [2]Part 1251 fact
    ctx:discord/blah/watt-activation/part-125
  3. [3]Part 2634 facts
    ctx:discord/blah/watt-activation/part-263
  4. [4]1253 facts
    ctx:discord/blah/watt-activation/125
    • full textwatt-activation-125
      text/plain3 KBdoc:agent/watt-activation-125/078b0573-153a-47f9-81de-fbf8dd1915e3
      Show excerpt
      [2026-03-09 03:33] xenonfun: ❯ we want to do 2K seq tho ⏺ Doubling seq doubles the activation memory. BS=8, seq=2048 = same logit tensor size as BS=16, seq=1024 — which hit 85GB. We need to re-check BS. BS=4, seq=2048 = 8,192 tokens/bat

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.