INDEX

Explanations

references to medical professionals with a specific focus on the title "Dr." and related rankings

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

dr followed by name or period

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

 Eisenberg

-0.60

eney

-0.55

gulier

-0.55

 Kearney

-0.54

ements

-0.53

 przód

-0.53

Ness

-0.52

yama

-0.52

ranean

-0.52

atah

-0.52

POSITIVE LOGITS

Dr

1.09

Dr

0.98

Drs

0.93

dr

0.86

 Doctor

0.75

 doctor

0.75

DR

0.71

 DOCTOR

0.71

 docteur

0.71

Doctor

0.70

Activations Density 0.016%

references to medical professionals with a specific focus on the title "Dr." and related rankings

dr followed by name or period

No Comments

No Known Activations