INDEX

Explanations

references to services and systems in an operational context

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

database of, scripts that

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 فريبيس

-0.39

AndEndTag

-0.35

 Viral

-0.34

asilkan

-0.34

 gerecht

-0.33

 Fluids

-0.33

 grze

-0.33

 Geophysics

-0.32

joner

-0.32

ThroughAttribute

-0.32

POSITIVE LOGITS

 Walkover

0.55

DockStyle

0.54

yntaxException

0.53

出版年

0.51

LookAnd

0.50

yarnpkg

0.48

oredCriteria

0.45

eload

0.45

HideInInspector

0.44

 ujednoznacz

0.43

Activations Density 0.102%

references to services and systems in an operational context

database of, scripts that

No Comments

No Known Activations