INDEX

Explanations

programming terms related to user interface layouts and menu inflation

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

UI layout inflation

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

UserScript

-0.46

writeFieldEnd

-0.43

 referenties

-0.43

лтамалар

-0.41

 Normdatei

-0.41

yelitis

-0.41

yarnpkg

-0.40

+#+#

-0.40

 PublicKey

-0.37

JKLM

-0.35

POSITIVE LOGITS

 Inflate

0.85

LookAnd

0.63

 useAppContext

0.59

 meille

0.56

RectangleBorder

0.54

astify

0.54

MenuInflater

0.52

setupUi

0.52

 ontwerp

0.51

OptionsMenu

0.50

Activations Density 0.000%

programming terms related to user interface layouts and menu inflation

UI layout inflation

No Comments

No Known Activations