INDEX

Explanations

phrases related to the activation or deactivation of systems or devices

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

ënten

-0.44

atrici

-0.43

erweise

-0.43

 leven

-0.42

ulity

-0.41

…

-0.39

тивні

-0.39

co

-0.39

mentaux

-0.39

POSITIVE LOGITS

 المعيارى

1.01

ConstraintMaker

0.89

 Monfieur

0.78

 Cæsar

0.76

AndEndTag

0.75

QMetaType

0.75

 myſelf

0.74

 فريبيس

0.73

 Италијани

0.72

 MenuView

0.71

Activations Density 0.283%

phrases related to the activation or deactivation of systems or devices

No Comments

No Known Activations