INDEX

Explanations

statements or claims related to dishonesty and misleading information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.38.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

SharedDtor

-0.60

IntoConstraints

-0.57

 فريبيس

-0.54

Cyfarwyddwr

-0.50

angor

-0.50

 समीक्षक

-0.50

 Италијани

-0.49

endphp

-0.48

SharedCtor

-0.48

blauch

-0.48

POSITIVE LOGITS

 deception

1.82

 fake

1.77

 deceiving

1.66

 faking

1.61

 deceit

1.61

 deceptive

1.60

 false

1.60

 faked

1.58

 deceive

1.57

 Fake

1.49

Activations Density 1.381%

statements or claims related to dishonesty and misleading information

No Comments

No Known Activations