INDEX

Explanations

terms related to programming structures and data organization

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

 uParam

-0.35

 olímp

-0.31

Recycle

-0.30

 Protección

-0.29

GM

-0.29

itrine

-0.28

ニーカー

-0.28

 estadual

-0.28

プーン

-0.28

 kasih

-0.28

POSITIVE LOGITS

SourceChecksum

0.66

 nahilalakip

0.56

достатки

0.52

migrationBuilder

0.52

 BufferedImage

0.49

liceerd

0.48

ByVersion

0.47

 հղումներ

0.47

 deklar

0.47

 ddelwed

0.47

Activations Density 0.431%

terms related to programming structures and data organization

No Comments

No Known Activations