INDEX

Explanations

technical terms and metrics related to statistical analysis and scientific reporting

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

or

-0.40

Personendaten

-0.37

 Wilderness

-0.36

yszer

-0.36

 honom

-0.35

 invokingState

-0.34

şu

-0.33

exitRule

-0.33

 máscaras

-0.33

 מז

-0.33

POSITIVE LOGITS

 كومونز

0.61

tonode

0.57

sidemargin

0.56

ChildScrollView

0.54

 AttributeSet

0.54

 StringTokenizer

0.53

oa̍t

0.53

slidesToShow

0.51

 Signalez

0.50

artifactId

0.49

Activations Density 1.101%

technical terms and metrics related to statistical analysis and scientific reporting

No Comments

No Known Activations