INDEX

Explanations

terms related to automotive performance features and modifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

antaranya

-0.50

 mukaan

-0.49

 aldri

-0.46

 compter

-0.45

 humaines

-0.45

 alkalmaz

-0.44

Embeddable

-0.43

mergeFrom

-0.43

 alapján

-0.43

 pomocą

-0.43

POSITIVE LOGITS

OGND

0.94

__':

0.89

 oprot

0.76

 Wicidata

0.71

 Aper

0.71

Personendaten

0.71

 Roskov

0.70

 motorsport

0.69

 racing

0.69

NFS

0.67

Activations Density 0.171%

terms related to automotive performance features and modifications

No Comments

No Known Activations