INDEX

Explanations

elements related to medical studies and technical details within scientific literature

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

RegressionTest

-0.63

jsxFileName

-0.60

Chham

-0.57

istoitu

-0.47

Personendaten

-0.46

codecSelfer

-0.42

Diweddarwch

-0.42

emlrt

-0.42

この時期

-0.42

存于互联网档案馆

-0.41

POSITIVE LOGITS

autoreleasepool

0.50

simpleType

0.41

GetAxis

0.40

 wireType

0.36

 onCreateView

0.36

 MainAxisSize

0.36

stdint

0.35

 BitmapFactory

0.35

 Harts

0.35

waitKey

0.34

Activations Density 1.152%

elements related to medical studies and technical details within scientific literature

No Comments

No Known Activations