INDEX

Explanations

structured mathematical formatting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

$?

-0.78

jectures

-0.77

fromnode

-0.77

__':

-0.76

rawDesc

-0.74

contentLoaded

-0.73

}?>

-0.73

хьтан

-0.72

]();

-0.72

 AspNetCore

-0.71

POSITIVE LOGITS

 Potsdam

0.84

 للاسماء

0.83

 Machu

0.69

 loch

0.68

 roux

0.68

 Estatal

0.67

 Sigism

0.65

 Caste

0.65

 Sentin

0.64

 Russians

0.63

Activations Density 0.010%

structured mathematical formatting

No Comments

No Known Activations