INDEX

Explanations

the start of a new document or section

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

ditor

-0.56

SuspendLayout

-0.56

 крю

-0.53

 bisous

-0.53

vœ

-0.52

 idéia

-0.51

esai

-0.50

Удачи

-0.50

 Turquie

-0.50

بیشتر

-0.49

POSITIVE LOGITS

:✨

1.47

✨:

1.16

✨

1.07

✨

0.97

✨✨

0.83

__(/*!

0.80

 NSCoder

0.78

uxxxx

0.67

__))

0.67

 تضيفلها

0.65

Activations Density 0.006%

the start of a new document or section

No Comments

No Known Activations