INDEX

Explanations

instances of articles (a, an, the) in the 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

 فريبيس

-0.97



-0.94

antMatchers

-0.83

GEBURTSDATUM

-0.82

 '\\;'

-0.80

OGND

-0.76

RenderAtEndOf

-0.76

RectangleBorder

-0.76

 kasarigan

-0.76

routeProvider

-0.75

POSITIVE LOGITS

 unique

0.70

ten

0.58

 also

0.55

mix

0.53

</caption>

0.52

two

0.52

 focus

0.51

 goal

0.50

 също

0.50

Activations Density 0.049%

instances of articles (a, an, the) in the text

No Comments

No Known Activations