INDEX

Explanations

terms related to user data and privacy policies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.30.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

пет

-0.33

 συμβ

-0.30

 espont

-0.30

creativecommons

-0.29

HttpDelete

-0.28

rån

-0.28

 fossils

-0.28

 surface

-0.28

 münd

-0.28

 Entstehung

-0.27

POSITIVE LOGITS

 mailing

1.08

 mail

1.02

 MAIL

0.96

 Mailing

0.96

 mails

0.94

 emails

0.93

 Mail

0.92

 email

0.91

mailing

0.90

 emailing

0.89

Activations Density 0.314%

terms related to user data and privacy policies

No Comments

No Known Activations