INDEX

Explanations

references to food and related topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

PageFactory

-0.82

Diweddarwch

-0.78

yntaxException

-0.75

granate

-0.72

EDEFAULT

-0.72

RegressionTest

-0.71

 aveug

-0.70

 arşivlendi

-0.69

 tachycardia

-0.66

rungsseite

-0.65

POSITIVE LOGITS

 food

4.38

 Food

3.88

food

3.80

Food

3.71

 FOOD

3.53

FOOD

3.27

 foods

2.90

 Foods

2.42

foods

2.34

食物

2.30

Activations Density 0.089%

references to food and related topics

No Comments

No Known Activations