INDEX

Explanations

references to medical degrees and qualifications of individuals

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

Academic titles (MD, PhD, MSc)

np_acts-logits-general · gemini-2.0-flash

academic and professional titles

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

Autoritní

-0.64

ConfigureAwait

-0.56

 désolés

-0.53

">';

-0.53

deelte

-0.50

amemnon

-0.50

 RouterModule

-0.49

}{*}{}

-0.49

 وتسجيلات

-0.48

yaf

-0.47

POSITIVE LOGITS

PhD

0.74

PhD

0.67

MENAFN

0.66

exels

0.55

styleUrls

0.53

 Founder

0.53

Esq

0.53

SaveChangesAsync

0.51

MSc

0.51

BSc

0.50

Activations Density 0.113%

references to medical degrees and qualifications of individuals

Academic titles (MD, PhD, MSc)

academic and professional titles

No Known Activations