INDEX

Explanations

phrases indicating product specifications and usability features

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

WireFormatLite

-0.48

المراجع

-0.45

 player

-0.45

 players

-0.44

 externes

-0.44

Források

-0.43

disconnected

-0.42

gie

-0.42

曖昧さ回避

-0.41

 anal

-0.41

POSITIVE LOGITS

 nonatomic

0.53

ConstraintMaker

0.48

enumi

0.48

AddHtmlAttribute

0.46

nonatomic

0.45

colhead

0.45

InitStruct

0.42

 AssemblyCompany

0.42

RTGC

0.41

IsMutable

0.40

Activations Density 0.001%

phrases indicating product specifications and usability features

No Comments

No Known Activations