INDEX

Explanations

mentions of email and notifications related to email usage

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

esModule

-0.45

 hObject

-0.43

PDOException

-0.41

DebuggerNonUser

-0.40

 NSCoder

-0.39

NegativeButton

-0.39

ouac

-0.37

agic

-0.37

PreferredItem

-0.37

WebServlet

-0.36

POSITIVE LOGITS

 unread

0.62

 propOrder

0.57

AndEndTag

0.47

unread

0.46

 notification

0.43

 unpaid

0.43

 متعلقه

0.43

✨:

0.43

 notifications

0.43

 нако

0.42

Activations Density 0.255%

mentions of email and notifications related to email usage

No Comments

No Known Activations