INDEX

Explanations

numerical data and patterns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 مشين

-0.63

出版年

-0.57

зулта

-0.57

KommentareTeilen

-0.53

 AssemblyCulture

-0.52

webElementXpaths

-0.52

</tfoot>

-0.51

 Consistency

-0.50

 CreateTagHelper

-0.50

.*")]

-0.49

POSITIVE LOGITS

BeginContext

0.61

zusetzen

0.55

]--;

0.54

mathit

0.53

ITES

0.53

 contextLoads

0.53

 ст

0.51

WriteBarrier

0.51

SOUNDBITE

0.51

 Neub

0.50

Activations Density 0.316%

numerical data and patterns

No Comments

No Known Activations