INDEX

Explanations

references to political scandals and ethical breaches

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

his private actions regarding alleged impropriety

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

 nahilalakip

-0.47

gan

-0.34

 launch

-0.32

 '\\;'

-0.29

 predict

-0.29

cho

-0.29

坑

-0.29

 inside

-0.29

árd

-0.29

 window

-0.28

POSITIVE LOGITS

vician

0.55

ſelben

0.55

ScopeManager

0.54

SharedDtor

0.54

tableFuture

0.51

BagConstraints

0.51

 CAMPAIGN

0.51

usercontent

0.50

EndProject

0.50

InjectAttribute

0.49

Activations Density 0.128%

references to political scandals and ethical breaches

his private actions regarding alleged impropriety

No Comments

No Known Activations