INDEX

Explanations

markers indicating 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 @ 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

 Silverman

-0.57

 Morales

-0.56

Rüyada

-0.56

zame

-0.54

 Greenberg

-0.54

 Silber

-0.52

 intStringLen

-0.51

tech

-0.50

 target

-0.50

 Tierney

-0.50

POSITIVE LOGITS

Personensuche

0.99

uxxxx

0.73

InjectAttribute

0.70

 Réponses

0.68

AutoScale

0.66

RectangleBorder

0.64

 odkazy

0.64

RegressionTest

0.62

 lenker

0.60

Geplaatst

0.59

Activations Density 0.061%

markers indicating the start of a new document or section

No Comments

No Known Activations