INDEX

Explanations

food-related vocabulary commonly associated with menu items and dining experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.41.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

httphttps

-0.46

енча

-0.45

EndGlobal

-0.45

FieldBuilder

-0.43

InjectAttribute

-0.42

 recevez

-0.42

 trouvez

-0.41

 Италијани

-0.41

recated

-0.41

 BrowserModule

-0.41

POSITIVE LOGITS

 dishes

1.04

 meals

0.91

 treats

0.82

 entrées

0.74

dishes

0.73

 breakfasts

0.73

 dinners

0.71

 delicacies

0.68

 entre

0.67

 creations

0.67

Activations Density 0.212%

food-related vocabulary commonly associated with menu items and dining experiences

No Comments

No Known Activations