INDEX

Explanations

numbers and statistical data within the text

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

oredCriteria

-0.67

RectangleBorder

-0.67

 utafitiHapana

-0.54

validates

-0.53

λυ

-0.53

verwijspagina

-0.52

 normal

-0.52

 tils

-0.52

 trou

-0.52

 ویکی‌پدی

-0.52

POSITIVE LOGITS

KommentareTeilen

0.70

__":

0.68

\{\\

0.63

ArgsConstructor

0.59

 venons

0.58

::_('

0.58

AnimationsModule

0.58

CloseOperation

0.57

נטרנט

0.56

struzione

0.56

Activations Density 0.082%

numbers and statistical data within the text

No Comments

No Known Activations