INDEX

Explanations

phrases related to quality and value in products or experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

onomía

-0.57

withIdentifier

-0.53

Personendaten

-0.53

 neutrons

-0.52

DbType

-0.51

 Femin

-0.50

().__

-0.48

 Baptists

-0.48

StrictMode

-0.48

 SqlDbType

-0.47

POSITIVE LOGITS

 jeweiligen

0.83

それぞれ

0.81

它們

0.76

 respective

0.75

どれも

0.74

それぞれの

0.73

 Administrativna

0.72

씩

0.71

 Each

0.71

 each

0.70

Activations Density 0.358%

phrases related to quality and value in products or experiences

No Comments

No Known Activations