INDEX

Explanations

specific terms and phrases related to names, titles, or identification across various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

ucksack

-0.57

RTLR

-0.57

 فريبيس

-0.56

 Xunit

-0.55

disposing

-0.55

entibus

-0.54

Spoiler

-0.53

 twain

-0.53

otene

-0.52

تقاوى

-0.51

POSITIVE LOGITS

帖最后由

0.65

 بيها

0.56

 تضيفلها

0.56

antaranya

0.50

 мәкалә

0.50

 mostrarán

0.49

*/;

0.47

*/;

0.46

الإنجليزية

0.46

)、

0.45

Activations Density 0.447%

specific terms and phrases related to names, titles, or identification across various contexts

No Comments

No Known Activations