INDEX

Explanations

references to pixels in images

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 InputDecoration

-0.80

ंदीखरीदारी

-0.78

createStatement

-0.69

fromCharCode

-0.68

 fratelli

-0.67

probs

-0.66

lapsingToolbar

-0.66

 acoper

-0.64

曖昧さ回避

-0.64

ArgsConstructor

-0.63

POSITIVE LOGITS

 pixels

3.06

 pixel

3.04

 Pixel

2.79

pixel

2.70

Pixel

2.66

pixels

2.59

 Pixels

2.57

PIXEL

2.32

Pixels

2.28

像素

1.97

Activations Density 0.060%

references to pixels in images

No Comments

No Known Activations