INDEX

Explanations

technical terms or elements related to digital and computational topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 otomatig

-0.69

EndProject

-0.65

 للاسماء

-0.61

Билгалдахарш

-0.59

-0.54

Примечания

-0.54

":[{

-0.51

onema

-0.47

WithMany

-0.46

antium

-0.46

POSITIVE LOGITS

ioutil

0.73

ècie

0.69

setupUi

0.68

ніципалі

0.64

ritsar

0.64

 JpaRepository

0.63

 TestBed

0.62

messageInfo

0.61

 itſelf

0.61

homonymie

0.60

Activations Density 0.807%

technical terms or elements related to digital and computational topics

No Comments

No Known Activations