INDEX

Explanations

punctuation and non-verbal expressions indicating emphasis or pauses in speech

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

PullParser

-0.69

MessageOf

-0.67

StoryboardSegue

-0.58

UrlResolution

-0.57

XmlAccessType

-0.56

исленность

-0.55

المشاركات

-0.54

 schlagen

-0.53

endforeach

-0.52

 BorderRadius

-0.52

POSITIVE LOGITS

 disambiguazione

0.53

nonatomic

0.49

erm

0.48

最早

0.47

 Grange

0.46

InSection

0.46

……"

0.46

ियाँ

0.46

 zasad

0.45

ieszka

0.45

Activations Density 0.242%

punctuation and non-verbal expressions indicating emphasis or pauses in speech

No Comments

No Known Activations