INDEX

Explanations

references to locations and associated entities

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

 tartalomajánló

-0.76

-£

-0.72

WriteTagHelper

-0.69

cillors

-0.69

Labour

-0.67

HtmlAttribute

-0.65

labour

-0.65

 Labour

-0.64

OGND

-0.64

 visualiser

-0.63

POSITIVE LOGITS

 America

0.93

 statunit

0.91

 امريكا

0.88

美国

0.88

USA

0.88

America

0.87

 Amerika

0.85

在美国

0.85

🇺🇸

0.82

US

0.81

Activations Density 1.621%

references to locations and associated entities

No Comments

No Known Activations