Dontopedia

Tanh

From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-09.)

Tanh has 7 facts recorded in Dontopedia across 3 references.

7 facts·6 predicates·3 sources

Mostly:preferred over normalize(1), constrains to interval(1), preserves relative magnitudes(1)

Maturity scale raw canonical shape-checked rule-derived certified

Inbound 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.

hasOptionHas Option(1)

Other facts (6)

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.

6 facts
PredicateValueRef
Preferred Over NormalizeL2 Normalize[1]
Constrains to Interval[-1,1][1]
Preserves Relative Magnitudestrue[1]
Has Propertyconstrains to [-1,1] per-dimension while preserving relative magnitudes[2]
Rdf:typeActivation Function[3]
Code Representation'tanh'[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.

preferredOverNormalizeblah/watt-activation/part-118
ex:l2-normalize
constrainsToIntervalblah/watt-activation/part-118
[-1,1]
preservesRelativeMagnitudesblah/watt-activation/part-118
true
hasPropertyblah/watt-activation/118
constrains to [-1,1] per-dimension while preserving relative magnitudes
typebeam/f503684f-0a28-4f83-a3dc-7b3be1874b77
ex:ActivationFunction
labelbeam/f503684f-0a28-4f83-a3dc-7b3be1874b77
Tanh
codeRepresentationbeam/f503684f-0a28-4f83-a3dc-7b3be1874b77
'tanh'

References (3)

3 references
  1. [1]Part 1183 facts
    ctx:discord/blah/watt-activation/part-118
  2. [2]1181 fact
    ctx:discord/blah/watt-activation/118
    • full textwatt-activation-118
      text/plain3 KBdoc:agent/watt-activation-118/ed79098d-1144-44f5-9941-e6b2b9c1caa7
      Show excerpt
      [2026-03-08 23:43] xenonfun: Code Changes (3 important patterns) 1. Fused QKV projection in SpectralAttention - Separate q_proj, k_proj, v_proj → single qkv_proj = Linear(d_model, 3 * d_model). One matmul instead of three. We should po
  3. ctx:claims/beam/f503684f-0a28-4f83-a3dc-7b3be1874b77
    • full textbeam-chunk
      text/plain1 KBdoc:beam/f503684f-0a28-4f83-a3dc-7b3be1874b77
      Show excerpt
      - **Example Values**: \(1e-5\), \(1e-4\), \(1e-3\), \(1e-2\), \(1e-1\). ### 2. **Batch Size** - **Description**: Number of samples processed before the model is updated. - **Range**: Typically between 8 and 512. - **Example Val

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.