INDEX

Explanations

numerical values related to image processing and scaling

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

numbers and mathematical operations

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

:✨

-0.60

+#+#

-0.58

ViewImports

-0.56

 Италијани

-0.55

 EconPapers

-0.54

 виправивши

-0.53

 propOrder

-0.51

RTLR

-0.51

__":

-0.50

 שוליים

-0.50

POSITIVE LOGITS

ResponseWriter

0.45

blurRadius

0.40

programmer

0.40

detectChanges

0.39

StandardCharsets

0.38

fromCharCode

0.38

levels

0.35

řel

0.35

 getItemId

0.35

max

0.35

Activations Density 0.007%

numerical values related to image processing and scaling

numbers and mathematical operations

No Comments

No Known Activations