INDEX

Explanations

mentions of specific automotive makes and models

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

getOutputStream

-0.54

 Libraries

-0.53

 directo

-0.53

zköz

-0.53

Huhu

-0.51

 dredge

-0.51

 library

-0.50

 organisational

-0.50

direkt

-0.50

 libraries

-0.50

POSITIVE LOGITS

 cars

0.95

 vehicles

0.87

 vehicle

0.85

 automobiles

0.79

cars

0.77

Cars

0.77

car

0.76

 Vehicles

0.75

 Automobiles

0.75

 Vehicle

0.75

Activations Density 0.412%

mentions of specific automotive makes and models

No Comments

No Known Activations