INDEX

Explanations

statistical trends and increases in various health-related metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.13.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

 بيها

-0.59

 &___

-0.57

verwijspagina

-0.55

RTEE

-0.53

transQ

-0.51

ніципалі

-0.50

 domani

-0.49

 amanhã

-0.48

ábado

-0.48

öhe

-0.48

POSITIVE LOGITS

didSet

0.76

 increase

0.73

decade

0.72

 trend

0.72

Бахар

0.70

increase

0.66

 decrease

0.65

Increases

0.65

 growth

0.64

 decline

0.63

Activations Density 0.068%

statistical trends and increases in various health-related metrics

No Comments

No Known Activations