INDEX

Explanations

references to popularity or popular items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

ValueStyle

-0.82

AntiForgeryToken

-0.74

gms

-0.68

elemField

-0.68

jooq

-0.65

énario

-0.64

hemiah

-0.63

anstalt

-0.62

BeginInit

-0.61

Sek

-0.60

POSITIVE LOGITS

 popular

1.98

popular

1.98

Popular

1.90

 Popular

1.87

 POPULAR

1.83

 populares

1.76

 popularity

1.67

 Popularity

1.57

 unpopular

1.50

 populer

1.49

Activations Density 0.032%

references to popularity or popular items

No Comments

No Known Activations