INDEX

Explanations

words and phrases associated with reviewing restaurants and their menus

oai_token-act-pair · gemini-2.0-flash

restaurant reviews

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

titleMargin

-0.52

IntoConstraints

-0.47

 EconPapers

-0.45

bootstrapcdn

-0.44

ăr

-0.44

 Италијани

-0.44

>>;

-0.42

 CURIAM

-0.42

 hospitality

-0.42

fälle

-0.41

POSITIVE LOGITS

<?

0.71

OGND

0.70

 MainAxisSize

0.67

///</

0.61

 textStatus

0.61

 MessageBoxIcon

0.60

UserScript

0.59

routeProvider

0.58

Kariera

0.56

LEncoder

0.56

Activations Density 2.371%

words and phrases associated with reviewing restaurants and their menus

restaurant reviews

No Comments

No Known Activations