Key Takeaway 1
From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-06.)
Key Takeaway 1 has 11 facts recorded in Dontopedia across 3 references, with 2 live disagreements.
Mostly:assesses performance(2), rdf:type(1), described by(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.
containsObservationContains Observation(1)
- Message 1
ex:message-1
Other facts (9)
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 |
|---|---|---|
| Assesses Performance | Model Config H40 | [3] |
| Assesses Performance | Model Config H48 | [3] |
| Rdf:type | Conclusion | [1] |
| Described by | 1 step >> 2 steps (PPL 243 vs 799) | [1] |
| Implies | more dynamics hurts gradient flow | [1] |
| Cited Evidence | PPL 243 vs 799 | [1] |
| Part of | Key Takeaways List | [2] |
| Consequence of | Rs Zero | [2] |
| Identifies Fast Configuration | Model Config H32 | [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/watt-activation/51- full textwatt-activation-51text/plain3 KB
doc:agent/watt-activation-51/53cd7634-6f49-4bb0-9083-629d07a48d10Show excerpt
[2026-03-07 07:59] xenonfun: ``` Full results are in. Here's the complete picture: ┌───────────────────┬───────────┬──────────┬──────┬──────────┬──────┐ │ Config │ Final PPL │ Best PPL │ r │ Clusters │ it/s │ ├─────────…
ctx:discord/blah/watt-activation/309- full textwatt-activation-309text/plain1 KB
doc:agent/watt-activation-309/2e41963d-8b19-4589-9c72-a02b6482ee90Show excerpt
[2026-03-15 00:18] xenonfun: claude's version. ``` Rotational strength is critical. RS=0.0 (pure AdamW) catastrophically fails at symbol formation — entropy 1.35, only 11 active codes. RS=0.2 gives best results. The angular update is essent…
ctx:discord/blah/watt-activation/677- full textwatt-activation-677text/plain2 KB
doc:agent/watt-activation-677/0a3c1f90-3dc6-48cb-b08e-24d6d4275edeShow excerpt
[2026-04-22 13:11] xenonfun: • For the H=40 preset (D=560, ~19.0M params), current measured GPU training is: ``` 21,642 tok/s at B=16, T=256 on M3 Ultra. I also tried nearby H values in multiples of 4: | H | D | Params | GPU tok/s |…
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.