INDEX

Explanations

references to Donald Trump and his actions or statements

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

"Trump"

np_acts-logits-general · gemini-2.0-flash

Donald Trump's words and actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 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

 autorytatywna

-0.53

XmlAccessType

-0.46

 fundamentally

-0.46

Carriera

-0.45

 disambiguazione

-0.43

吋

-0.43

PG

-0.42

ंदीखरीदारी

-0.41

榴

-0.41

 Paglinawan

-0.39

POSITIVE LOGITS

 Trump

0.95

Trump

0.88

trump

0.66

特朗普

0.57

 trump

0.52

Donald

0.52

 Donald

0.52

 ترام

0.49

 donald

0.49

DialogContent

0.49

Activations Density 0.237%

references to Donald Trump and his actions or statements

"Trump"

Donald Trump's words and actions

No Comments

No Known Activations