INDEX

Explanations

terms and phrases related to medical conditions, particularly psychiatric disorders and their diagnostic criteria

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 pinulongan

-0.44

MENAFN

-0.42

Климат

-0.38

BibitemShut

-0.38

 cardiaque

-0.37

ırlı

-0.36

 autorytatywna

-0.36

Clik

-0.35

 Temp

-0.35

bibinfo

-0.35

POSITIVE LOGITS

 StatelessWidget

0.59

aarrggbb

0.56

 createSprite

0.49

 HasFactory

0.49

 StatefulWidget

0.47

discovery

0.47

ItemBackground

0.47

mvn

0.46

 Mérimée

0.45

 AppComponent

0.45

Activations Density 0.881%

terms and phrases related to medical conditions, particularly psychiatric disorders and their diagnostic criteria

No Comments

No Known Activations