INDEX

Explanations

programmatic functions related to creating and manipulating Excel files

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

creating spreadsheets

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

تقاوى

-0.73

omyia

-0.73

Cyfeiriadau

-0.67

 Dietz

-0.60

pushFollow

-0.59

__':

-0.59

GEBURTSDATUM

-0.59

 Sanders

-0.58

 sand

-0.56

 unknownFields

-0.56

POSITIVE LOGITS

 sheet

1.85

sheet

1.79

Sheet

1.78

 Sheet

1.76

 sheets

1.67

 SHEET

1.67

 Sheets

1.60

SHEET

1.57

Excel

1.54

excel

1.53

Activations Density 0.032%

programmatic functions related to creating and manipulating Excel files

creating spreadsheets

No Comments

No Known Activations