INDEX

Explanations

patterns of numerical data or structural relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

Unmarshaller

-0.63

 NSCoder

-0.55

HasColumnType

-0.55

MessageTagHelper

-0.54

InvalidProtocol

-0.54

Extinguishing

-0.53

TemporalType

-0.50

MockBean

-0.49

yii

-0.49

coroutines

-0.49

POSITIVE LOGITS

出版年

0.63

 ويكيميديا

0.61

￡

0.59

popd

0.57

 edelstahl

0.56

 ***!

0.56

KommentareTeilen

0.55

 autorytatywna

0.54

منم

0.54

GNA

0.54

Activations Density 0.322%

patterns of numerical data or structural relationships

No Comments

No Known Activations