INDEX

Explanations

terms related to health and healthcare management

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

"Health" followed by a word relating to care or professionals

np_acts-logits-general · gemini-2.0-flash

health care services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

EndContext

-0.91

 préciser

-0.65

 igång

-0.63

IsContent

-0.58

midler

-0.57

 незавершена

-0.56

 ainfi

-0.56

 conclure

-0.56

Kilder

-0.55

 définiti

-0.54

POSITIVE LOGITS

 GenerationType

0.67

']>;

0.61

">//

0.60

 ویکی‌پدیا

0.56

//

0.56

NUMX

0.55

 uParam

0.54

richTextPanel

0.52

#+#

0.51

 StatelessWidget

0.51

Activations Density 1.230%

terms related to health and healthcare management

"Health" followed by a word relating to care or professionals

health care services

No Comments

No Known Activations