INDEX

Explanations

phrases expressing gratitude or appreciation

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

"Thanks for"

np_acts-logits-general · gemini-2.0-flash

thanks for

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

Personensuche

-0.49

himself

-0.46

 himself

-0.46

 tertentu

-0.45

أن

-0.43

 Himself

-0.43

 المكت

-0.42

 AppColors

-0.42

ormick

-0.41

 generales

-0.40

POSITIVE LOGITS

AutoScale

0.87

 ddelweddau

0.86

новниш

0.81

 kaynağından

0.80

tagext

0.77

parsedMessage

0.74

 snippetHide

0.70

IsContent

0.70

 للمعارف

0.70

 autorytatywna

0.68

Activations Density 0.064%

phrases expressing gratitude or appreciation

"Thanks for"

thanks for

No Comments

No Known Activations