INDEX

Explanations

occurrences of scripting elements within the document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

matchCondition

-0.55

̈́

-0.50

+:+

-0.48

sizeCache

-0.47

 comenzaron

-0.47

ujen

-0.46

nœ

-0.46

 comenzó

-0.45

 Guilford

-0.45

 Taktlose

-0.45

POSITIVE LOGITS

script

1.05

endphp

0.95

 مرئيه

0.81

ChildScrollView

0.78

//

0.72

Chham

0.66

SCRIPT

0.66

})();

0.65

脚注の使い方

0.61

 VIDEOTAPE

0.61

Activations Density 0.031%

occurrences of scripting elements within the document

No Comments

No Known Activations