INDEX

Explanations

imperative phrases and suggestions for actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

esistenza

-0.52

endsection

-0.50

withOpacity

-0.45

tableFuture

-0.42

Prof

-0.41

 useContext

-0.41

prof

-0.39

 enemy

-0.38

getDoctrine

-0.38

 Mountain

-0.38

POSITIVE LOGITS

Давайте

0.66

 Vamos

0.63

 Lets

0.63

 للاسماء

0.59

Vamos

0.59

Lets

0.59

きましょう

0.58

Let

0.56

})$}

0.54

let

0.52

Activations Density 0.151%

imperative phrases and suggestions for actions

No Comments

No Known Activations