INDEX

Explanations

indications of boredom or feelings of inactivity

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

killing time

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

Personensuche

-0.62

 simplifié

-0.54

 resourceCulture

-0.52

IBOutlet

-0.50

styleType

-0.48

脚注の使い方

-0.48

ConstraintMaker

-0.47

ValueStyle

-0.45



-0.44

findpost

-0.44

POSITIVE LOGITS

 boredom

1.39

 bored

1.20

bored

0.98

 idle

0.97

无聊

0.95

 Bored

0.89

Bored

0.82

暇

0.80

 idleness

0.79

 Bore

0.78

Activations Density 0.041%

indications of boredom or feelings of inactivity

killing time

No Comments

No Known Activations