INDEX

Explanations

references to healthcare providers and medical professionals

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

medical professionals

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

ⓧ

-0.59

thâu

-0.58

postIndex

-0.51

 freshness

-0.50

parsedMessage

-0.50

 wikipagina

-0.48

Espèce

-0.46

튿

-0.46

 Extinction

-0.45

 Vaux

-0.45

POSITIVE LOGITS

 physician

0.65

 doctor

0.58

 physicians

0.56

 doctors

0.56

 Physician

0.49

 dokter

0.48

 prescribe

0.47

 médecins

0.46

CrossRef

0.45

 JpaRepository

0.44

Activations Density 0.022%

references to healthcare providers and medical professionals

medical professionals

No Comments

No Known Activations