INDEX

Explanations

references to pixels and pixel-related concepts 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 @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

-0.93

lapsingToolbar

-0.79

CWE

-0.79

 acoper

-0.78

 doInBackground

-0.77

ंदीखरीदारी

-0.75

ectady

-0.73

EnableWeb

-0.72

oa̍t

-0.70

moveToFirst

-0.69

POSITIVE LOGITS

 pixels

2.12

 pixel

1.96

 Pixel

1.90

Pixel

1.79

 Pixels

1.78

pixels

1.78

pixel

1.73

Pixels

1.65

PIXEL

1.64

像素

1.32

Activations Density 0.034%

references to pixels and pixel-related concepts in images

No Comments

No Known Activations