INDEX

Explanations

formatted data structures and their relationships

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

');?>

-0.70

TintMode

-0.69

oredCriteria

-0.59

++]=

-0.57

</em>

-0.56

]='\

-0.54

UnusedPrivate

-0.53

 متعلقه

-0.53

:][

-0.52

 дописавши

-0.52

POSITIVE LOGITS

Personendaten

0.68

出版年

0.63

̈́

0.57

 الحره

0.53

Odkazy

0.53

 StatelessWidget

0.51

 Audiodateien

0.50

 zvuky

0.48

Джерела

0.48

numerusform

0.48

Activations Density 1.536%

formatted data structures and their relationships

No Comments

No Known Activations