INDEX

Explanations

instructions related to cooking processes

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

pholes

-0.47

makeConstraints

-0.47

Наводи

-0.46

 picture

-0.45

 cream

-0.45

KindOfClass

-0.45

Lor

-0.44

 scene

-0.44

refront

-0.44

 march

-0.44

POSITIVE LOGITS

OGND

0.49

 ويكيميديا

0.46

SharedDtor

0.45

IsContent

0.44

parsedMessage

0.41

JspWriter

0.38

GOTREF

0.38

eamiento

0.37

ScopeManager

0.37

 Réponses

0.36

Activations Density 0.197%

instructions related to cooking processes

No Comments

No Known Activations