INDEX

Explanations

phrases related to questions and logical reasoning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 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

 those

-0.62

那些

-0.56

 /\.(

-0.54

Externé

-0.53

those

-0.52

 intptr

-0.49

après

-0.49

slidesToShow

-0.48

 Италијани

-0.48

@[+][

-0.48

POSITIVE LOGITS

AddHtmlAttribute

0.68

del

0.65

VersionUID

0.61

 newBuilder

0.59

 della

0.59

tvguidetime

0.55

 AssemblyCulture

0.54

 TestBed

0.47

ثيق

0.47

例文帳に追加

0.47

Activations Density 0.046%

phrases related to questions and logical reasoning

No Comments

No Known Activations