INDEX

Explanations

references to specific types of biological or chemical entities, particularly in a clinical or experimental context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

}))

-0.83

 pinulongan

-0.80

})));

-0.75

 Mukherjee

-0.72

ılıyor

-0.71

}));

-0.71

 betweenstory

-0.71

 Morty

-0.68

 Espinosa

-0.67

='')

-0.67

POSITIVE LOGITS

 MainAxisSize

0.94

AccessFile

0.85

 HasFactory

0.84

AnimationFrame

0.83

PAH

0.79

EAP

0.78

 Wayback

0.77

 navideñas

0.76

GAP

0.76

WAC

0.75

Activations Density 3.148%

references to specific types of biological or chemical entities, particularly in a clinical or experimental context

No Comments

No Known Activations