INDEX

Explanations

cooking instructions or recipe-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 BorderSide

-0.54

 flips

-0.54

cshtml

-0.53

UpInside

-0.53

 Inse

-0.52

 Nutella

-0.52

 gymnast

-0.52

 Issa

-0.51

 sushi

-0.50

serviceWorker

-0.50

POSITIVE LOGITS

 broth

1.09

 soup

1.09

 Broth

0.94

 stock

0.91

 Soup

0.89

soup

0.85

 thickened

0.83

 soups

0.80

Soup

0.80

 stocks

0.79

Activations Density 0.168%

cooking instructions or recipe-related terms

No Comments

No Known Activations