INDEX

Explanations

references to clinical trial data and medical measurements

oai_token-act-pair · gpt-4o-mini Triggered by @bot

Quantities of patients, points, vehicles, etc

np_acts-logits-general · gemini-2.0-flash

quantities of entities

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ujednoznacz

-0.52

writeFieldEnd

-0.52

 BoxDecoration

-0.51

sizeCache

-0.50

IntoConstraints

-0.50

:✨

-0.46

帖最后由

-0.45

 surla

-0.45

addContainerGap

-0.45

">//

-0.44

POSITIVE LOGITS

 averaging

0.49

 distributed

0.48

 annually

0.47

distributed

0.47

 queued

0.46

 thousand

0.43

 registered

0.41

IonicModule

0.41

のうち

0.41

 ranging

0.41

Activations Density 0.482%

references to clinical trial data and medical measurements

Quantities of patients, points, vehicles, etc

quantities of entities

No Comments

No Known Activations