INDEX

Explanations

references to specific figures or illustrations 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

idere

-0.49

 Haines

-0.47

bij

-0.46

 NgModule

-0.45

bl

-0.45

 traje

-0.44

 leases

-0.44

surate

-0.44

 Thacker

-0.43

டுத்த

-0.43

POSITIVE LOGITS

 مشين

0.81

\{\\

0.78

 referenties

0.76

)‏

0.74

 ligiloj

0.73

ंदीखरीदारी

0.71

зулта

0.71

']))

0.69

findpost

0.68

}))

0.68

Activations Density 0.003%

references to specific figures or illustrations in the text

No Comments

No Known Activations