INDEX

Explanations

specific scientific terms or measurements

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

statistical and quantitative terms

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

endregion

-0.46

providedIn

-0.46

enumi

-0.43

AddTagHelper

-0.38

onViewCreated

-0.35

 متعلقه

-0.35

//

-0.34

makeText

-0.34

SuspendLayout

-0.34

kunft

-0.34

POSITIVE LOGITS

Personendaten

0.69

 ويكيپيديا

0.63

Jeografia

0.62

 EnglishChoose

0.61

copg

0.61

 мәкал

0.60

 المعيارى

0.58

astéro

0.57

 Мексичка

0.57

ंदीखरीदारी

0.54

Activations Density 0.145%

specific scientific terms or measurements

statistical and quantitative terms

No Comments

No Known Activations