harmonic_coeffs
From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-06.)
harmonic_coeffs is G×H learned frequency weights.
Mostly:rdf:type(3), structured as(1), initializes groups(1)
Maturity scale
raw canonical shape-checked rule-derived certifiedInbound mentions (6)
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.
couldNotFindLiveAttentionPathUseForCould Not Find Live Attention Path Use for(1)
- Xenonfun
ex:xenonfun
includesIncludes(1)
- Oscillator Params
ex:oscillator-params
removedCodeRemoved Code(1)
- Xenonfun
ex:xenonfun
updatesUpdates(1)
- V2
ex:v2
updatesParameterUpdates Parameter(1)
- Oscillator Param Update
ex:oscillator-param-update
wasJustInitializingTensorAndNeverReadingWas Just Initializing Tensor and Never Reading(1)
- Attention
ex:attention
Other facts (14)
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 |
|---|---|---|
| Rdf:type | Parameter | [4] |
| Rdf:type | Model Parameter | [6] |
| Rdf:type | Model Parameter | [7] |
| Structured As | Cos Ω G·k | [1] |
| Initializes Groups | [:, 1] = 1.0 | [1] |
| Is Gtimes H | True | [2] |
| Was Completely Dangling in | Lohe Spherical Attention | [3] |
| Had Gradient Magnitude | 0 | [4] |
| Needs Room to | evolve | [5] |
| Updated in Version | v2 | [7] |
| Description | G×H learned frequency weights | [7] |
| Was Dangling in | Lohe Spherical Attention | [8] |
| Has No Live Use | Attention Path | [8] |
| Located in Repo | Legacy Ffn Branches | [8] |
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 (8)
ctx:discord/blah/watt-activation/part-184ctx:discord/blah/watt-activation/part-210ctx:discord/blah/watt-activation/part-261ctx:discord/blah/watt-activation/190- full textwatt-activation-190text/plain3 KB
doc:agent/watt-activation-190/afd2a2d6-55fc-43d9-9655-83cd2755213fShow excerpt
[2026-03-10 03:51] xenonfun: ⏺ The fix is working. Here's the comparison: ``` ┌────────────────┬────────────────┬────────────────────────────┐ │ Metric │ Before fix │ After fix │ ├────────────────┼────────…
ctx:discord/blah/watt-activation/192- full textwatt-activation-192text/plain3 KB
doc:agent/watt-activation-192/c3ca4e62-2524-47f4-9e3e-6cb28f08f78cShow excerpt
[2026-03-10 04:10] xenonfun: ⏺ Working correctly now. Full comparison: ```┌──────────────────────┬────────────────────┬─────────────────────────┐ │ │ RotAdamW fine-tune │ LoheOptimizer fine-tune │ ├─────────────────…
ctx:discord/blah/watt-activation/198- full textwatt-activation-198text/plain2 KB
doc:agent/watt-activation-198/ea2dbbd7-7d1c-4ba2-9281-56322a048288Show excerpt
[2026-03-10 06:11] xenonfun: ``` ⏺ --- Summary #1 — features tensor restored One line in lohe_ffn.py. The optimizer already had the branch ready (if 'features' in metrics:). What activates now: - W_out[:, 32..92] (weighted harmon…
ctx:discord/blah/watt-activation/209- full textwatt-activation-209text/plain2 KB
doc:agent/watt-activation-209/d7eabcf9-d506-432f-9a2c-b25cf5ef8ccdShow excerpt
[2026-03-11 03:51] xenonfun: ```# coupling (K) and adjacency are structural constants — not updated. 598 + # v2: update harmonic_coeffs (G×H learned frequency weights) 599 + # v3: update mode_amplitudes (k scalars,…
ctx:discord/blah/watt-activation/259- full textwatt-activation-259text/plain3 KB
doc:agent/watt-activation-259/b2e296e0-fb4d-4e37-8eb5-edb6b6f98d8dShow excerpt
[2026-03-12 20:52] ajaxdavis: they got a frontend role, im gonna apply for my own made up role on their behalf somewhere in between [2026-03-12 21:10] xenonfun: its pretty rough at visuals, forgetting axis labels other things but it works w…
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.