INDEX

Explanations

punctuation that indicates questions and statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

кож

-0.97

Anyway

-0.77

 تضيفلها

-0.74

 επίσης

-0.73

 justement

-0.72

}>;

-0.71

igens

-0.70

 Anyway

-0.69

dû

-0.69

ilarang

-0.68

POSITIVE LOGITS

 Suddenly

0.59

And

0.53

Suddenly

0.52

这一刻

0.52

 suddenly

0.51

Yet

0.51

 Bukan

0.50

 Gone

0.48

Gone

0.48

yet

0.46

Activations Density 0.223%

punctuation that indicates questions and statements

No Comments

No Known Activations