INDEX

Explanations

markup or syntactical elements in programming or script code

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

HTML tags or attributes

np_acts-logits-general · gemini-2.0-flash

HTML and script tags

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

endphp

-0.92

出版年

-0.71

nameof

-0.70

principalColumn

-0.68

 BoxFit

-0.68

وأضاف

-0.63

RetentionPolicy

-0.63

SaveChangesAsync

-0.61

anyol

-0.60

NSIndexPath

-0.58

POSITIVE LOGITS

<table>

0.56

vician

0.50

<?

0.49

 brah

0.47

 ExecuteAsync

0.47

ंदीखरीदारी

0.47

bewerken

0.46

WindowConstants

0.46

RUnlock

0.45

Activations Density 0.090%

markup or syntactical elements in programming or script code

HTML tags or attributes

HTML and script tags

No Known Activations