INDEX

Explanations

terms related to user logout actions and dropout in studies

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

dropout from studies

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.24.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

-0.53

 betrekking

-0.49

 eventId

-0.48

Simply

-0.44

 Simply

-0.44

 jsonArray

-0.44

 materialen

-0.43

ientôt

-0.43

thums

-0.43

~•

-0.42

POSITIVE LOGITS

Logout

1.18

 logout

1.18

logout

1.14

 Logout

1.13

LOGOUT

1.04

logOut

0.78

 Hout

0.68

LogOut

0.66

outbound

0.65

gout

0.64

Activations Density 0.008%

terms related to user logout actions and dropout in studies

dropout from studies

No Comments

No Known Activations