INDEX

Explanations

prepositions and articles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

>{@

-0.63

ciaż

-0.55

ÚBL

-0.53

יצד

-0.50

 noop

-0.50

abstractmethod

-0.49

).__

-0.49

 bình

-0.48

ceria

-0.48

⎦

-0.48

POSITIVE LOGITS

forName

0.81

ⓧ

0.78

elemField

0.74

 connaît

0.72

GraphicsUnit

0.71

esez

0.69

 adanya

0.69

XtraReports

0.67

 snippetHide

0.67

Personendaten

0.66

Activations Density 0.281%

prepositions and articles

No Comments

No Known Activations