INDEX

Explanations

words relating to product reviews and updates

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

Tokens after punctuation

np_acts-logits-general · gemini-2.0-flash

alpha notation in formulas

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

ütün

-0.54

amique

-0.53

 scenery

-0.53

 androidx

-0.51

"}")

-0.50

})`

-0.50

omans

-0.50

uksessa

-0.50

 magnétique

-0.50

RuleContext

-0.50

POSITIVE LOGITS

uxxxx

0.81

ⓧ

0.80

saraba

0.64

 cherchés

0.58

DeleteBehavior

0.56

Filed

0.55

存于互联网档案馆

0.54

UPDATE

0.54

richTextPanel

0.54

下载附件

0.53

Activations Density 0.159%

words relating to product reviews and updates

Tokens after punctuation

alpha notation in formulas

No Comments

No Known Activations