INDEX

Explanations

beginnings of texts or statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

NYC

-0.67

 seperate

-0.65

…

-0.64

 FREE

-0.62

Carriera

-0.59

เค้า

-0.59

yrs

-0.56

はコチラ

-0.56

 kinda

-0.56

 govt

-0.56

POSITIVE LOGITS

AndEndTag

0.90

SourceChecksum

0.65

 Paglinawan

0.64

SequentialGroup

0.63

الحياه

0.62

"""

0.59

 Савезне

0.57

 AspNetCore

0.56

']],

0.56

gettyimages

0.56

Activations Density 0.031%

beginnings of texts or statements

No Comments

No Known Activations