INDEX

Explanations

French language question phrases, often using the forms "que," "-t-", "je", and "peut".

oai_token-act-pair · gemini-2.0-flash

French and code snippets

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

帖最后由

-0.65

 Sementara

-0.63

it

-0.56

 SwitchCompat

-0.55

 inmedi

-0.54

It

-0.53

us

-0.52

BeginInit

-0.52

 them

-0.51

 Enquanto

-0.51

POSITIVE LOGITS

withIdentifier

0.60

genstein

0.59

']?>

0.53

viewDidLoad

0.52

rebro

0.52

 propOrder

0.50

 StyleSheet

0.50

ﷺ

0.50

')['

0.50

iostream

0.50

Activations Density 0.509%

French language question phrases, often using the forms "que," "-t-", "je", and "peut".

French and code snippets

No Comments

No Known Activations