INDEX

Explanations

instances of names associated with specific individuals or organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

reactstrap

-0.43

 sepanjang

-0.42

getDoctrine

-0.41

uttosto

-0.41

hoea

-0.40

atterns

-0.40

pes

-0.40

шкан

-0.39

om

-0.39

filters

-0.39

POSITIVE LOGITS

SourceChecksum

0.90

CloseOperation

0.90

TagMode

0.85

IsContent

0.79

aarrggbb

0.76

 ErrIntOverflow

0.76

 kasarigan

0.75

 nahilalakip

0.73

 autorytatywna

0.71

#+#

0.67

Activations Density 0.339%

instances of names associated with specific individuals or organizations

No Comments

No Known Activations