INDEX

Explanations

terminology related to medical diagnoses and treatments

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

"brain" or parts of the brain

np_acts-logits-general · gemini-2.0-flash

brain metastases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

mybatisplus

-0.61

 RoutedEventArgs

-0.58

Portail

-0.57

Życiorys

-0.54

 JpaRepository

-0.53

parametrize

-0.53

xda

-0.53

hoto

-0.52

 palmar

-0.51

buk

-0.51

POSITIVE LOGITS

 brain

1.20

 brains

1.13

brain

1.01

 Brain

0.99

 Brains

0.99

Brain

0.95

brains

0.95

Brains

0.93

 BRAIN

0.89

 cere

0.85

Activations Density 0.722%

terminology related to medical diagnoses and treatments

"brain" or parts of the brain

brain metastases

No Comments

No Known Activations