INDEX

Explanations

references to research support and funding acknowledgments

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

AndEndTag

-0.99

principalTable

-0.99

تقاوى

-0.97

+#+#

-0.91

LookAnd

-0.91

InitVars

-0.83

Personensuche

-0.81

Personendaten

-0.81

OGND

-0.78

 surla

-0.78

POSITIVE LOGITS

效

0.48

wark

0.48

 primarily

0.46

 متعل

0.46

 exclusively

0.45

IRECT

0.45

 notamment

0.45

makta

0.45

den

0.45

Activations Density 0.572%

references to research support and funding acknowledgments

No Comments

No Known Activations