INDEX

Explanations

terminology related to administrative divisions and boundaries

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

Geplaatst

-0.82

SourceChecksum

-0.77

 NSCoder

-0.77

 MainAxisSize

-0.75

AnimationsModule

-0.73

 WebDriverWait

-0.71

 ivelany

-0.70

titleMargin

-0.70

DeleteBehavior

-0.70

 typelib

-0.70

POSITIVE LOGITS

 defined

0.63

 boundaries

0.52

 based

0.48

defined

0.48

 deline

0.46

 delineated

0.46

 DbSet

0.46

切れ

0.45

划分

0.45

sidian

0.43

Activations Density 0.590%

terminology related to administrative divisions and boundaries

No Comments

No Known Activations