INDEX

Explanations

terms related to health assessments and healthcare recommendations

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

GOTREF

-0.79

tagHelperRunner

-0.72

 Италијани

-0.59

HomeAsUpEnabled

-0.58

fjspx

-0.58

rativo

-0.51

rungsseite

-0.50

 للمعارف

-0.49

Erz

-0.49

PreferredItem

-0.48

POSITIVE LOGITS

 checkup

1.16

 annual

1.11

 yearly

1.08

 routine

1.06

 inspection

1.05

Annual

1.04

 screenings

1.04

 screening

1.02

 examinations

1.02

 Periodic

1.00

Activations Density 0.417%

terms related to health assessments and healthcare recommendations

No Comments

No Known Activations