INDEX

Explanations

statements regarding political behavior and cabinet positions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/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.19.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

Carriera

-0.64

 electing

-0.55

ISupport

-0.51

 conquistar

-0.51

HOA

-0.51

abestanden

-0.48

 rigging

-0.48

KommentareTeilen

-0.47

ViewImports

-0.47

 géné

-0.47

POSITIVE LOGITS

 ministry

1.34

 Cabinet

1.27

 Ministry

1.27

 Minister

1.26

 ministerial

1.23

 minister

1.19

 Secretary

1.17

 cabinet

1.16

minist

1.15

 Department

1.13

Activations Density 0.426%

statements regarding political behavior and cabinet positions

No Comments

No Known Activations