INDEX

Explanations

technical terms and measurements in a medical or scientific context

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

person or thing followed by description

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.16.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

 שוליים

-0.52

iconque

-0.46

is

-0.42

fortawesome

-0.42

Aktualisiert

-0.41

featureID

-0.41

раздо

-0.40

مراجع

-0.40

 transfieras

-0.40

出版年

-0.39

POSITIVE LOGITS

are

1.29

 were

1.26

 são

0.90

Datuak

0.90

 zostały

0.89

were

0.87

 έχουν

0.86

 đều

0.85

 jsou

0.85

 weren

0.84

Activations Density 0.534%

technical terms and measurements in a medical or scientific context

person or thing followed by description

No Comments

No Known Activations