INDEX

Explanations

terms related to healthcare treatment and recall information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

AndEndTag

-0.63

UrlResolution

-0.61

gså

-0.58

 tường

-0.53

too

-0.48

 Jüng

-0.48

too

-0.47

@}

-0.44

muth

-0.43

enseits

-0.43

POSITIVE LOGITS

ConstraintMaker

0.78

rungsseite

0.67

SharedDtor

0.65

providedIn

0.63

 CreateTagHelper

0.63

 Autorizaciones

0.63

KommentareTeilen

0.61

__':

0.60

IsInitialized

0.60

Activations Density 0.608%

terms related to healthcare treatment and recall information

No Comments

No Known Activations