INDEX

Explanations

references to dishonesty and deception

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

 poco

-0.37

はじめに

-0.36

clientWidth

-0.34

 tartalomajánló

-0.34

Autoritní

-0.33

Aholisi

-0.33

 EUROPE

-0.32

gig

-0.32

ernoo

-0.32

冷冷

-0.31

POSITIVE LOGITS

 falsehood

0.74

 mentira

0.73

 truthful

0.71

 mentiras

0.70

 dishonest

0.66

 liars

0.65

 dishonesty

0.65

 liar

0.64

 lying

0.64

 lied

0.63

Activations Density 0.563%

references to dishonesty and deception

No Comments

No Known Activations