INDEX

Explanations

keywords and terms related to programming and system operations

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 disambiguazione

-0.50

 Erben

-0.50

rawDesc

-0.50

 Psicología

-0.48

 Vielen

-0.46

nezeu

-0.46

########.

-0.45

SourceChecksum

-0.45

ValueStyle

-0.44

ViewFeatures

-0.43

POSITIVE LOGITS

 ligiloj

0.57

 فريبيس

0.43

prefixer

0.43

 kasarigan

0.42

 nahilalakip

0.42

Diwedd

0.40

 оригіналу

0.39

SUC

0.38

vább

0.37

Activations Density 0.662%

keywords and terms related to programming and system operations

No Known Activations