INDEX

Explanations

references to the White House and the concept of "white."

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

"White"

np_acts-logits-general · gemini-2.0-flash

white followed by a noun phrase

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

NameInMap

-0.92

__":

-0.86

 bezeichneter

-0.77

rrggbb

-0.77

клопе

-0.71

tagHelperRunner

-0.71

__":

-0.70

__':

-0.69

FormTagHelper

-0.68

 ImportError

-0.68

POSITIVE LOGITS

 White

1.12

White

1.03

 WHITE

1.00

WHITE

0.99

 white

0.97

white

0.93

 Whites

0.92

Whites

0.84

白

0.80

 blanca

0.79

Activations Density 0.066%

references to the White House and the concept of "white."

"White"

white followed by a noun phrase

No Comments

No Known Activations