INDEX

Explanations

references to products and their features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 considérons

-0.55

meyi

-0.49

férés

-0.46

pbs

-0.46

 notoriety

-0.46

Publicado

-0.46

рованной

-0.45

racy

-0.45

ног

-0.45

 formalized

-0.44

POSITIVE LOGITS

 product

1.18

 merchandise

1.01

 AssemblyCulture

0.97

 ProductService

0.96

product

0.96

 ArrayAdapter

0.94

});*/

0.93

};*/

0.90

 Product

0.90

 PRODUCT

0.89

Activations Density 0.132%

references to products and their features

No Comments

No Known Activations