INDEX

Explanations

terms related to medical professionals and their qualifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

Derbyniad

-0.56

SharedCtor

-0.44

 gyhoeddwyd

-0.43

autogui

-0.38

 informée

-0.38

 Hewitt

-0.38

Numerology

-0.38

arraycopy

-0.37

 ANGELES

-0.36

Obfuscated

-0.36

POSITIVE LOGITS

 physician

0.80

 doctor

0.76

 physicians

0.75

doctor

0.74

 doctors

0.72

 Physician

0.70

 Doctor

0.69

physician

0.69

 Doctors

0.69

Doctor

0.66

Activations Density 0.477%

terms related to medical professionals and their qualifications

No Comments

No Known Activations