INDEX

Explanations

technical references to APIs and data models

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

references to healthcare and medical terminology, especially related to healthcare systems, facilities, and professional roles.

oai_token-act-pair · claude-3-5-haiku-20241022 Triggered by @neilrathi

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68

Prompts (Dashboard)

24,576 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Süß

-0.33

 Gründ

-0.31

zit

-0.30

Ớ

-0.30

 κε

-0.30

 rebaj

-0.30

bulkan

-0.30

 Sedangkan

-0.29

 pasaran

-0.29

vaig

-0.29

POSITIVE LOGITS

 hospitals

1.04

 hospital

1.02

Hospitals

0.95

 Hospital

0.93

Hospital

0.90

 healthcare

0.89

 Hospitals

0.88

 Healthcare

0.84

Healthcare

0.84

 Medicare

0.82

Activations Density 0.289%

technical references to APIs and data models

references to healthcare and medical terminology, especially related to healthcare systems, facilities, and professional roles.

No Comments

No Known Activations