INDEX

Explanations

references to locations or entities associated with a status of significance or prominence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

ollectionView

-0.63

الإنجليزية

-0.59

EFE

-0.56

IBAction

-0.56

dbus

-0.54

cnpj

-0.53

EFE

-0.52

ViewFeatures

-0.50

 UITableView

-0.49

opengl

-0.48

POSITIVE LOGITS

Portail

0.75

 فريبيس

0.67

throughout

0.66

HOUT

0.65

Tembelea

0.64

 Entire

0.62

 ErrIntOverflow

0.62

Entire

0.61

ImageContext

0.60

nitř

0.60

Activations Density 0.379%

references to locations or entities associated with a status of significance or prominence

No Comments

No Known Activations

references to locations or entities associated with a status of significance or prominence

No Comments

No Known Activations