INDEX

Explanations

references to sections and subsections in documents

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

 ModelExpression

-0.57

Mapped

-0.50

}*/

-0.49

كويكب

-0.49

Organized

-0.48

 NUKAT

-0.48

 colonnes

-0.48

 estekak

-0.48

 getrennt

-0.47

 Bean

-0.46

POSITIVE LOGITS

Sec

0.97

Sec

0.80

sec

0.79

GEBURTSDATUM

0.69

sec

0.64

getDoctrine

0.63

seck

0.63

invokeLater

0.63

 typelib

0.62

 textStatus

0.62

Activations Density 0.159%

references to sections and subsections in documents

No Comments

No Known Activations