INDEX

Explanations

keywords related to health metrics and treatments

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

Acronyms followed by lowercase letters

np_acts-logits-general · gemini-2.0-flash

common acronyms

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

Not in Any Lists

No Comments

Negative Logits

出版年

-0.77

 سكانية

-0.64

);*/

-0.60

();

-0.58

 useNavigate

-0.56

 препратки

-0.56

 mouseY

-0.56

──

-0.55

}}-

-0.54

ρώ

-0.54

POSITIVE LOGITS

 HttpNotFound

0.69

aaS

0.62

 disponibilités

0.62

kezik

0.59

Cllr

0.59

ⓘ

0.59

inderella

0.58

 tromper

0.58

ẠI

0.58

 flèche

0.58

Activations Density 1.086%

keywords related to health metrics and treatments

Acronyms followed by lowercase letters

common acronyms

No Comments

No Known Activations