INDEX

Explanations

numerical data and references throughout a scientific text

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

Tokens after numbers and superscripts

np_acts-logits-general · gemini-2.0-flash

figures and footnotes

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

-0.91

-0.82

-0.70

 geográfica

-0.55

-0.54

iredo

-0.47

-0.46

-0.45

progressbar

-0.44

POSITIVE LOGITS

脚注の使い方

0.86

 MessageBoxIcon

0.84

ⓧ

0.82

ItemBackground

0.77

出版年

0.73

<?

0.69

 useStyles

0.68

 ویکی‌پدیای

0.67

"@/

0.64

 nahilalakip

0.64

Activations Density 0.956%

numerical data and references throughout a scientific text

Tokens after numbers and superscripts

figures and footnotes

No Comments

No Known Activations