Small Linear Layer
From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-06.)
Small Linear Layer has 4 facts recorded in Dontopedia across 2 references.
Mostly:attached on top of(1), fine tuned on(1), attached to(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.
requiresRequires(1)
- Proper Probe Evaluation
ex:proper-probe-evaluation
Other facts (4)
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 |
|---|---|---|
| Attached on Top of | Get Sync Embedding Function | [1] |
| Fine Tuned on | Classification Task | [1] |
| Attached to | Get Sync Embedding Model Function | [2] |
| Processing Mode | Fine Tune | [2] |
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 (2)
ctx:discord/blah/watt-activation/part-224ctx:discord/blah/watt-activation/223- full textwatt-activation-223text/plain2 KB
doc:agent/watt-activation-223/5ca6c9c7-cd04-43a7-bc21-d7dc83321f1bShow excerpt
[2026-03-11 05:06] xenonfun: oh that was older checkpoint ... ⏺ The probe works. But this checkpoint uses spectral+lohe_v2 (not v3), so no mode_power field. The r values are flat across blocks (0.49–0.63) — that's expected for eval mode o…
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.