INDEX

Explanations

terms related to pixel data and its manipulation

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

 acoper

-0.75

 InputDecoration

-0.74

ंदीखरीदारी

-0.68

lapsingToolbar

-0.66

 cortas

-0.64

 matières

-0.64

रीदारी

-0.63

 heridos

-0.62

 fratelli

-0.62

Története

-0.62

POSITIVE LOGITS

 pixels

2.42

 pixel

2.28

 Pixel

2.13

pixels

2.06

 Pixels

2.03

Pixel

2.02

pixel

2.02

Pixels

1.85

PIXEL

1.84

像素

1.49

Activations Density 0.077%

terms related to pixel data and its manipulation

No Comments

No Known Activations