INDEX

Explanations

terms related to locations and geographical areas

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.35.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 Latin

-0.55

 Spanish

-0.52

 Brazilian

-0.52

 Mexican

-0.50

 Argentine

-0.50

 Chilean

-0.49

 Brazil

-0.47

 LATIN

-0.47

 Peruvian

-0.46

Latin

-0.44

POSITIVE LOGITS

 kemajuan

0.52

 autorytatywna

0.47

 betweenstory

0.47

Personensuche

0.46

convite

0.46

PostInfinity

0.45

 věci

0.45

llavero

0.45

 мәкал

0.43

 nikdy

0.43

Activations Density 0.194%

terms related to locations and geographical areas

No Known Activations