INDEX

Explanations

phrases that express uncertainty or complexity in reasoning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 فريبيس

-0.46

KURZBESCHREIBUNG

-0.43

 الاطلاع

-0.42

SpringBootTest

-0.38

UpInside

-0.38

-0.36

initWithFrame

-0.35

sizeCache

-0.34

BeginContext

-0.33

 comigo

-0.33

POSITIVE LOGITS

 Administrativna

0.56

Susie

0.52

 Susie

0.52

crisy

0.49

bcryptjs

0.48

 Pirelli

0.48

ACO

0.47

LEC

0.47

ARB

0.47

ecycle

0.47

Activations Density 6.215%

phrases that express uncertainty or complexity in reasoning

No Comments

No Known Activations