INDEX

Explanations

terms related to scientific research and explanation

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

bitkan

-0.52

MLLoader

-0.52

WriteLiteral

-0.52

 firebaseConfig

-0.50

Chances

-0.49

udic

-0.46

 Conſ

-0.45

ųjų

-0.44

仕

-0.44

 davon

-0.43

POSITIVE LOGITS

verwijspagina

0.72

AsUp

0.70

łgorzata

0.59

AndEndTag

0.58

adaptiveStyles

0.58

 MainAxisSize

0.58

Legături

0.58

XmlAccessType

0.57

ModelAdmin

0.57

UARY

0.56

Activations Density 0.584%

terms related to scientific research and explanation

No Comments

No Known Activations