INDEX

Explanations

references to academic papers and research studies

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

 <>",

-0.29

 APPRO

-0.28

 meccan

-0.27

 ejerc

-0.26

 nejs

-0.26

 ANIMALS

-0.26

 animaux

-0.25

ativamente

-0.25

readlines

-0.25

 affirmé

-0.25

POSITIVE LOGITS

 AssemblyCompany

0.79

setVerticalGroup

0.77

 booklet

0.74

CloseOperation

0.70

richTextPanel

0.69

HtmlAttribute

0.68

DockStyle

0.68

adaptiveStyles

0.65

 EconPapers

0.65

ThroughAttribute

0.64

Activations Density 0.219%

references to academic papers and research studies

No Comments

No Known Activations