INDEX

Explanations

references to healthcare policies and regulations

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

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

 وتسجيلات

-0.84

 autorytatywna

-0.65

 pinulongan

-0.64

AddTagHelper

-0.63

 bride

-0.63

tagHelperRunner

-0.62

rungsseite

-0.59

delwed

-0.59

 groom

-0.58

tagHelper

-0.58

POSITIVE LOGITS

 coverage

1.03

 Medicare

0.99

 insurance

0.91

 Medicaid

0.91

 Coverage

0.89

coverage

0.86

 uninsured

0.86

 Obamacare

0.85

Medicare

0.82

 cover

0.82

Activations Density 0.224%

references to healthcare policies and regulations

No Comments

No Known Activations