INDEX

Explanations

specific terminology related to automotive parts and services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Marburg

-0.55

 sostegno

-0.51

">—

-0.50

 saites

-0.50

 humaine

-0.50

 polaire

-0.49

 plufieurs

-0.47

 sedia

-0.47

 Rabbi

-0.47

 Davos

-0.46

POSITIVE LOGITS

 vehicle

1.42

 cars

1.31

car

1.30

 Vehicle

1.28

 automotive

1.27

 vehicles

1.24

 automobile

1.21

Vehicle

1.21

 Automotive

1.18

vehicle

1.18

Activations Density 0.314%

specific terminology related to automotive parts and services

No Comments

No Known Activations