INDEX

Explanations

references to various types of offices and office-related terminology

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

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

 propOrder

-0.80

LEncoder

-0.78

enumii

-0.73

ribune

-0.70

+:+

-0.69

Tembelea

-0.69

nt

-0.66

 فريبيس

-0.66

 تضيفلها

-0.65

ImageContext

-0.65

POSITIVE LOGITS

 offices

0.83

 Offices

0.70

 OFFICES

0.69

 office

0.66

 OFFICE

0.66

offices

0.63

 Office

0.62

 Büro

0.61

Geplaatst

0.59

లాలు

0.59

Activations Density 0.069%

references to various types of offices and office-related terminology

No Comments

No Known Activations