INDEX

Explanations

technical terms and medical nomenclature related to treatments and conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 Андрей

-0.50

vej

-0.49

 Deixe

-0.49

 compren

-0.48

EUA

-0.47

dracht

-0.46

Humph

-0.46

}}}}

-0.45

ευ

-0.45

 well

-0.45

POSITIVE LOGITS

 يتيمه

0.80

abestanden

0.74

 ويكيميديا

0.71

Espèce

0.70

 HasFactory

0.69

 mouth

0.68

 насељу

0.67

 cage

0.66

 صوتيه

0.66

 Vikipedi

0.66

Activations Density 2.341%

technical terms and medical nomenclature related to treatments and conditions

No Comments

No Known Activations