INDEX

Explanations

references to specific TV series and episodes

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

"of" followed by a noun or series

np_acts-logits-general · gemini-2.0-flash

TV show episodes and series

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

tagext

-0.67

enterOuterAlt

-0.55

 بيها

-0.51

Географиясе

-0.48

$\

-0.47

bnf

-0.45

 &___

-0.44

ьаж

-0.44

__*/

-0.44

marshaller

-0.43

POSITIVE LOGITS

Efq

0.83

最快更新

0.71

 doubtnut

0.70

 مرئيه

0.69

 Houſe

0.62

$_"

0.62

}();

0.61



0.60

 Theſe

0.59

 programmes

0.59

Activations Density 0.240%

references to specific TV series and episodes

"of" followed by a noun or series

TV show episodes and series

No Comments

No Known Activations