INDEX

Explanations

references to supplementary materials and publication details in academic contexts

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

media and image repositories

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_32/width_131k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.32.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

atguigu

-0.48

rédients

-0.44

styleUrls

-0.43

脚注の使い方

-0.42

AndroidJUnit

-0.39

Fontes

-0.39

 tolua

-0.38

MigrationBuilder

-0.38

AntiForgeryToken

-0.37

뀐

-0.37

POSITIVE LOGITS

存于互联网档案馆

0.56

 images

0.56

 image

0.53

Mediabestanden

0.53

Commons

0.50

imedia

0.49

 imagens

0.48

 alberga

0.48

 Image

0.47

 immagini

0.46

Activations Density 0.001%

references to supplementary materials and publication details in academic contexts

media and image repositories

No Comments

No Known Activations