INDEX

Explanations

terms related to health and healthcare

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

"Health" followed by words like "care," "workers," or "issues."

np_acts-logits-general · gemini-2.0-flash

health care workers and issues

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ConstraintMaker

-0.95

 للاسماء

-0.78

ništ

-0.76

astéro

-0.73

 وتسجيلات

-0.73

 ErrIntOverflow

-0.72

 CreateTagHelper

-0.72

RectangleBorder

-0.66

yntaxException

-0.66

ISupport

-0.66

POSITIVE LOGITS

 care

0.89

ier

0.66

 Care

0.65

cares

0.59

span

0.59

ily

0.57

iest

0.56

CARE

0.56

Care

0.56

care

0.51

Activations Density 0.090%

terms related to health and healthcare

"Health" followed by words like "care," "workers," or "issues."

health care workers and issues

No Comments

No Known Activations