INDEX

Explanations

punctuation marks and formatting elements in the text

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

Follows a name

np_acts-logits-general · gemini-2.0-flash

negative predictive

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

mbggenerated

-0.66

határoz

-0.56

Достоинства

-0.55

daß

-0.54

beleid

-0.53

endregion

-0.52

ISSN

-0.52

้อมูล

-0.50

UnusedPrivate

-0.50

Applies

-0.49

POSITIVE LOGITS

Fans

0.88

 Fans

0.83

 fans

0.82

 Earlier

0.72

 Ahead

0.69

 Needless

0.69

fans

0.69

ล่า

0.68

 Speaking

0.68

Speaking

0.68

Activations Density 0.127%

punctuation marks and formatting elements in the text

Follows a name

negative predictive

No Comments

No Known Activations