INDEX

Explanations

references to bathrooms and shower-related items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

存于互联网档案馆

-0.66

atuor

-0.63

 QtCore

-0.63

antart

-0.61

nskap

-0.60

XmlAccessType

-0.60

geddon

-0.59

 nodeId

-0.59

ruvate

-0.59

ENDIAN

-0.58

POSITIVE LOGITS

 shower

0.87

shower

0.74

 bidet

0.74

🚿

0.72

 bathroom

0.71

Shower

0.70

 showers

0.68

 Showers

0.67

 Shower

0.66

 ванной

0.65

Activations Density 0.064%

references to bathrooms and shower-related items

No Comments

No Known Activations