INDEX

Explanations

terms associated with physical fitness and exercise

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 Depp

-0.71

 Normdatei

-0.70

MethodManager

-0.70

uttavia

-0.69

BeginContext

-0.65

 Caspian

-0.61

 crescent

-0.61

 ujednoznacz

-0.60

ismuth

-0.59

 <<<<<<<<<<<<<<

-0.58

POSITIVE LOGITS

 workout

2.32

 exercise

2.04

 workouts

1.96

 Workout

1.93

 Exercise

1.83

 exercising

1.81

exercise

1.80

Exercise

1.79

workout

1.76

 fitness

1.75

Activations Density 0.086%

terms associated with physical fitness and exercise

No Comments

No Known Activations