INDEX

Explanations

references to photographs or photo-related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

]-->

-0.74

rils

-0.70

 EconPapers

-0.69

])]

-0.69

IsPostBack

-0.68

})$}

-0.68

كويكب

-0.67

írus

-0.66

+',

-0.65

 majeurs

-0.65

POSITIVE LOGITS

 photo

2.01

 photos

1.92

photo

1.87

Photo

1.84

 Photo

1.83

 PHOTO

1.75

 Photos

1.71

Photos

1.68

photos

1.65

PHOTO

1.59

Activations Density 0.041%

references to photographs or photo-related concepts

No Comments

No Known Activations