INDEX

Explanations

references to Java and org-compliant library imports

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

Personendaten

-1.32

featureID

-1.11

IUrlHelper

-1.07

GEBURTSDATUM

-1.06

windowFixed

-1.02

 itſelf

-1.00

PreferredItem

-0.98

 étoient

-0.98

AsUp

-0.97

LookAnd

-0.97

POSITIVE LOGITS

0.58

0.57

0.54

vra

0.52

0.49

0.48

athery

0.47

0.46

<unused63>

0.46

0.45

Activations Density 0.022%

references to Java and org-compliant library imports

No Comments

No Known Activations