INDEX

Explanations

occurrences of signs and indications of medical conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

hdashline

-0.57

 Wikispecies

-0.53

 Lombardo

-0.53

 abstracts

-0.53

 greateſt

-0.52

 fatale

-0.52

 whoſe

-0.52

zeczytaj

-0.52

 colspan

-0.52

 Pingback

-0.52

POSITIVE LOGITS

 signs

0.95

 Signs

0.85

Signs

0.83

 signes

0.82

 signos

0.79

 SIGNS

0.77

signs

0.76

 tanda

0.76

zeichen

0.74

 sign

0.73

Activations Density 0.239%

occurrences of signs and indications of medical conditions

No Comments

No Known Activations