INDEX

Explanations

references to the concept of "wholeness" or entirety

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

'",

-0.73

 limestones

-0.69

 DataTypes

-0.66

ic

-0.65

brücken

-0.64

Ellis

-0.63

Cuisine

-0.63

 Aniston

-0.63

'";

-0.63

 Tapatalk

-0.60

POSITIVE LOGITS

 whole

1.98

whole

1.95

Whole

1.90

 Whole

1.83

 entire

1.82

 WHOLE

1.80

entire

1.53

 Entire

1.53

 ENTIRE

1.42

Entire

1.40

Activations Density 0.049%

references to the concept of "wholeness" or entirety

No Comments

No Known Activations