INDEX

Explanations

references to the term "white" in various contexts

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Negative Logits

/*

-0.78

})`

-0.77

 henvisninger

-0.76

نگار

-0.75

ScopeManager

-0.72

FormTagHelper

-0.72

 Gusto

-0.71

rung

-0.71

awtextra

-0.70

 okuyayım

-0.69

POSITIVE LOGITS

 White

1.71

White

1.56

 Whites

1.55

WHITE

1.46

 WHITE

1.43

 white

1.41

white

1.34

Whites

1.34

 whites

1.27

 Whitehead

1.23

Activations Density 0.040%

references to the term "white" in various contexts

No Known Activations