INDEX

Explanations

discussions related to studies, specifically around healthcare, patient outcomes, and research findings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

mis

-0.46

 ListTile

-0.44

 later

-0.43

utebol

-0.42

Motors

-0.42

しょ

-0.41

ertos

-0.41

Hoff

-0.41

her

-0.40

vi

-0.40

POSITIVE LOGITS

contentLoaded

0.90

出版年

0.76

esModule

0.74

asgi

0.73

 getSource

0.70

 LoggerFactory

0.69

extAlignment

0.69

RefNanny

0.65

FundMe

0.65

ыгана

0.64

Activations Density 2.885%

discussions related to studies, specifically around healthcare, patient outcomes, and research findings

No Comments

No Known Activations