INDEX

Explanations

markers indicating the beginning of new sections or significant entries in a text

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

dimension and type

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.16.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

WebVitals

-0.96

 AssemblyCulture

-0.82

 مشين

-0.76

 nahilalakip

-0.75

Autoritní

-0.75

Portail

-0.72

Obrázky

-0.70

 insuffisamment

-0.68

MemoryWarning

-0.63

 transfieras

-0.62

POSITIVE LOGITS

 متحده

0.56

Übersicht

0.48

下载附件

0.46

 serangga

0.45

 Meksiku

0.45

tonode

0.45

backers

0.43

featureID

0.43

pherals

0.42

ftagPool

0.42

Activations Density 0.326%

markers indicating the beginning of new sections or significant entries in a text

dimension and type

No Comments

No Known Activations