INDEX

Explanations

references to physical activity or exercise

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

lliant

-0.87

contentLoaded

-0.81

 GIPHY

-0.80

луй

-0.78

CEEDED

-0.76

orghini

-0.75

 bénévol

-0.74

fordable

-0.74

 líquida

-0.73

úsqueda

-0.73

POSITIVE LOGITS

 exercises

1.55

 exercise

1.51

 EXERCISE

1.49

 Exercise

1.46

 Exercises

1.42

Exercise

1.39

Exercises

1.35

 Exer

1.32

exercise

1.24

EXERCISE

1.22

Activations Density 0.092%

references to physical activity or exercise

No Comments

No Known Activations