INDEX

Explanations

references to "white" and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/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.19.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

NameInMap

-1.03

 bezeichneter

-0.85

__":

-0.80

MessageTagHelper

-0.77

 CreateTagHelper

-0.75

bewerken

-0.74

FormTagHelper

-0.74

rrggbb

-0.74

yntaxException

-0.73

 MenuView

-0.72

POSITIVE LOGITS

 White

1.32

White

1.23

 white

1.16

 WHITE

1.13

WHITE

1.12

white

1.10

 Whites

1.06

Whites

0.93

白

0.91

 blanca

0.85

Activations Density 0.088%

references to "white" and related terms

No Comments

No Known Activations