INDEX

Explanations

references to the concept of "one" or singularity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

ly

-0.72

 ―――――

-0.72

 București

-0.68

CrossRef

-0.67

tably

-0.67

 Bettina

-0.65

Cec

-0.65

titian

-0.64

 totales

-0.64

 Dorset

-0.62

POSITIVE LOGITS

One

1.23

ONE

1.17

One

1.12

 hundred

0.97

ONE

0.97

one

0.95

☝

0.94

one

0.93

 OneNote

0.89

 Oneida

0.88

Activations Density 0.167%

references to the concept of "one" or singularity

No Comments

No Known Activations