INDEX

Explanations

dates and time-related references in text

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

processable

-0.49

TableHead

-0.47

DialogContent

-0.47

Посилання

-0.46

INSEE

-0.44

 resourceCulture

-0.43

featureID

-0.40

 continuant

-0.40

şiv

-0.39

 Commemor

-0.39

POSITIVE LOGITS

Tembelea

0.93

 المعيارى

0.82

 مرئيه

0.79

ueux

0.72

PreferredItem

0.71

存于互联网档案馆

0.70

]){

0.70

原始内容存档于

0.69

 acepción

0.68

 thereunder

0.68

Activations Density 0.033%

dates and time-related references in text

No Comments

No Known Activations