INDEX

Explanations

PHP closing tags

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

<?php ?> tags

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

Negative Logits

 Мексичка

-0.59

 Италијани

-0.59

 Савезне

-0.57

 ویکی‌پدی

-0.56

enumi

-0.54

Gön

-0.53

AndEndTag

-0.49

 يتيمه

-0.48

Tembelea

-0.47

TabLayout

-0.47

POSITIVE LOGITS

?>

1.49

?>

1.42

?>

1.34

endphp

1.22

?>

1.13

{?>

1.11

;?>

1.08

}?>

1.05

{?>

1.01

);?>

0.96

Activations Density 0.001%

PHP closing tags

<?php ?> tags

No Known Activations