INDEX

Explanations

LaTeX commands related to images and figures

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

LaTeX environments and labels

np_acts-logits-general · gemini-2.0-flash

LaTeX labels and environments

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

queryInterface

-0.87

NameInMap

-0.69

WriteTagHelper

-0.65

ssohn

-0.62

?')

-0.60

protoimpl

-0.57

thâu

-0.57

 mergeFrom

-0.56

Havolalar

-0.54

")));

-0.54

POSITIVE LOGITS

end

0.61

caption

0.60

</blockquote>

0.51

InBytes

0.49

 lepto

0.49

 חיצוניים

0.48

 captioned

0.48

\\

0.48

StringLiteral

0.48

Activations Density 0.142%

LaTeX commands related to images and figures

LaTeX environments and labels

LaTeX labels and environments

No Comments

No Known Activations