INDEX

Explanations

references to government or political accusations involving violence or injustice

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

 disambiguazione

-0.55

 Hints

-0.50

 مشين

-0.50

 propOrder

-0.50

Tikang

-0.49

ніципалі

-0.49

expandindo

-0.47

ViewFeatures

-0.47

 familiarize

-0.46

 vistazo

-0.46

POSITIVE LOGITS

 quæ

0.34

 deſt

0.34

脚注の使い方

0.30

승

0.30

autoFocus

0.28

DataMember

0.28

 ſtre

0.28

 XCTest

0.27

mybatisplus

0.27

 againſt

0.27

Activations Density 0.458%

references to government or political accusations involving violence or injustice

No Comments

No Known Activations