INDEX

Explanations

references to series in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

itects

-0.73

mette

-0.69

lihood

-0.69

脚注の使い方

-0.69

 toothpick

-0.68

 notizia

-0.67

сылкі

-0.67

kadot

-0.66

utdown

-0.66

olesome

-0.65

POSITIVE LOGITS

 series

1.96

 Series

1.92

Series

1.88

 SERIES

1.80

series

1.65

iseries

1.63

SERIES

1.60

 Serie

1.24

eries

1.21

Serie

1.19

Activations Density 0.034%

references to series in various contexts

No Comments

No Known Activations