INDEX

Explanations

parentheses and error-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

InjectAttribute

-0.66

Geplaatst

-0.59

HasAnnotation

-0.59

izr

-0.55

">//

-0.53

 الاطلاع

-0.51

HasOne

-0.51

 voluto

-0.50

 Superhost

-0.49

bootstrapcdn

-0.49

POSITIVE LOGITS

VersionUID

1.60

 noqa

1.06

spath

1.04

@[+][

0.99

 StatefulWidget

0.78

脚注の使い方

0.71

CPtr

0.64

 Parcelable

0.61

disposing

0.60

tvguidetime

0.59

Activations Density 0.006%

parentheses and error-related terms

No Comments

No Known Activations