INDEX

Explanations

references to email and email-related terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132

Prompts (Dashboard)

24,576 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

 planten

-0.44

 soorten

-0.44

 herói

-0.41

 natuur

-0.40

 fatores

-0.39

 ListNode

-0.39

таратура

-0.39

 circonstances

-0.38

alanta

-0.38

 punte

-0.38

POSITIVE LOGITS

 email

1.54

 Email

1.40

Email

1.39

 emails

1.30

email

1.26

 EMAIL

1.24

 emailing

1.23

Emails

1.16

getEmail

1.16

 emailed

1.15

Activations Density 0.102%

references to email and email-related terminology

No Comments

No Known Activations

references to email and email-related terminology

No Comments

No Known Activations