INDEX

Explanations

references to political figures and their actions

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

the president or presidency

np_acts-logits-general · gemini-2.0-flash

Oval Office and White House occupancy

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

-0.59

IContainer

-0.54

abestanden

-0.51

 JpaRepository

-0.49

 للمعارف

-0.49

dersfield

-0.48

矶

-0.47

Seeder

-0.46

ավ

-0.46

 cherchés

-0.45

POSITIVE LOGITS

 presidential

1.37

 Presidential

1.34

Presidential

1.29

 President

1.28

 presidencial

1.27

President

1.18

 presidency

1.18

 Presidency

1.14

 PRESIDENT

1.12

 présidenti

1.10

Activations Density 0.266%

references to political figures and their actions

the president or presidency

Oval Office and White House occupancy

No Comments

No Known Activations