INDEX

Explanations

phrases related to medical advice and patient-provider interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.38.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

 otomatig

-0.59

 Patienten

-0.55

NameInMap

-0.50

 mxArray

-0.49

patients

-0.49

 pacientes

-0.48

Patients

-0.47

ovatel

-0.46

 Patients

-0.46

 patienter

-0.46

POSITIVE LOGITS

 doctor

1.35

 doctors

1.29

 physician

1.21

 physicians

1.16

doctor

1.05

doctors

0.96

 Doctor

0.96

 dentist

0.95

医生

0.92

 dokter

0.90

Activations Density 0.631%

phrases related to medical advice and patient-provider interactions

No Comments

No Known Activations