INDEX

Explanations

references to availability or features of options or schedules

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

math and technical terms

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

saraba

-0.85

Geplaatst

-0.84

DeleteBehavior

-0.83

sizeCache

-0.75

 للاسماء

-0.74

PreferredItem

-0.71

 feroit

-0.70

SaveVideo

-0.70

 consultato

-0.68

/**

-0.68

POSITIVE LOGITS

<h3>

0.89

<h2>

0.83

<h6>

0.78

<h4>

0.77

<h1>

0.71

<h5>

0.64

%%

0.56

NSNotification

0.51

jön

0.51

GNUC

0.48

Activations Density 0.002%

references to availability or features of options or schedules

math and technical terms

No Comments

No Known Activations