INDEX

Explanations

terms related to the medical field

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Aron

-0.46

Bewer

-0.46

arande

-0.43

 Mullen

-0.43

สมบัติ

-0.42

 Nachhal

-0.41

Potencia

-0.41

 Winkler

-0.41

 disfruta

-0.41

 StringTokenizer

-0.40

POSITIVE LOGITS

 medical

1.13

 medically

1.08

 Medical

1.05

 doctors

1.04

 physicians

1.03

medical

1.01

Medical

1.01

 healthcare

1.00

 Physicians

0.93

 physician

0.93

Activations Density 0.542%

terms related to the medical field

No Comments

No Known Activations