INDEX

Explanations

expressions of gratitude or thanks

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

thank you

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

UnsafeEnabled

-0.78

 ujednoznacz

-0.71

VersionUID

-0.70

 Numerade

-0.65

 disambiguazione

-0.64

Personendaten

-0.62

KommentareTeilen

-0.61

rungsseite

-0.60

 հղումներ

-0.59

astéroïdes

-0.59

POSITIVE LOGITS

Thank

1.27

 Thank

0.99

 thank

0.98

thank

0.88

THANK

0.73

 THANK

0.71

<bos>

0.68

Vielen

0.59

Thanks

0.58

 thanked

0.56

Activations Density 0.007%

expressions of gratitude or thanks

thank you

No Comments

No Known Activations