INDEX

Explanations

references to plates used in serving food and dining contexts

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

 للاسماء

-0.80

RectangleBorder

-0.79

"])

-0.76

 تضيفلها

-0.72

']],

-0.68

uxta

-0.68

"]);

-0.67

rored

-0.67

észetes

-0.65

ंदीखरीदारी

-0.65

POSITIVE LOGITS

 plate

0.97

plate

0.84

 Plate

0.83

Plate

0.82

 PLATE

0.79

 plates

0.69

 dish

0.68

PLATE

0.65

 PLATES

0.63

 dishes

0.61

Activations Density 0.112%

references to plates used in serving food and dining contexts

No Comments

No Known Activations