INDEX

Explanations

numerical identifiers or codes related to various entities or elements

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

 couvercle

-0.68

 Trow

-0.65

ှ

-0.64

WORTH

-0.63

ENEFITS

-0.63

bew

-0.62

Slu

-0.62

pecially

-0.62

ularia

-0.61

 éché

-0.61

POSITIVE LOGITS

MigrationBuilder

0.95

CloseOperation

0.74

 estekak

0.71

ftagPool

0.70

хьтан

0.70

 تانيه

0.69

nonatomic

0.69

 nonatomic

0.66

 resourceCulture

0.66

 smtplib

0.64

Activations Density 0.206%

numerical identifiers or codes related to various entities or elements

No Comments

No Known Activations