INDEX

Explanations

medical terms related to diagnoses and treatments

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

"1" followed mostly by time units

np_acts-logits-general · gemini-2.0-flash

time periods measured in weeks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

rungsseite

-0.76

出版年

-0.75

Lähteet

-0.75

 disambiguazione

-0.74

########.

-0.74

CloseOperation

-0.73

IntoConstraints

-0.73

Personensuche

-0.73

 autorytatywna

-0.71

 editions

-0.66

POSITIVE LOGITS

third

0.72

 third

0.71

 thing

0.70

 single

0.63

 week

0.59

 bénéfices

0.57

 vecka

0.55

 vœux

0.54

 attentes

0.54

 person

0.54

Activations Density 0.311%

medical terms related to diagnoses and treatments

"1" followed mostly by time units

time periods measured in weeks

No Comments

No Known Activations