INDEX

Explanations

references to authority and regulatory frameworks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

脚注の使い方

-0.77

Portale

-0.62

">—

-0.62

]-->

-0.59

awtextra

-0.55

enis

-0.54

Handlung

-0.53

ืน

-0.50

Lig

-0.49

OGND

-0.49

POSITIVE LOGITS

 under

1.68

Under

1.59

 Under

1.52

under

1.45

 UNDER

1.34

Bajo

1.29

 bajo

1.28

UNDER

1.22

neath

1.11

 bawah

1.10

Activations Density 0.206%

references to authority and regulatory frameworks

No Comments

No Known Activations