INDEX

Explanations

words commonly found in online advertisements for fashion

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

webElementXpaths

-0.81

Personendaten

-0.76

èdia

-0.71

kuuta

-0.65

Portail

-0.64

 OFDb

-0.63

oredCriteria

-0.60

OrNil

-0.60

EDEFAULT

-0.60

DebuggerNonUser

-0.59

POSITIVE LOGITS

+#+#

0.57

numerusform

0.53

 ويكيميديا

0.52

/***/

0.50

Hochspringen

0.45

 porcelaine

0.44

 onCancelled

0.43

AMG

0.43

ms

0.42

 varsa

0.41

Activations Density 3.160%

words commonly found in online advertisements for fashion

No Comments

No Known Activations