INDEX

Explanations

references to prime ministers and their roles

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

preceding "Minister" or "prime factors"

np_acts-logits-general · gemini-2.0-flash

Prime Minister

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/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.24.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

principalColumn

-0.63

 nakalista

-0.62

 ProtoMessage

-0.61

 JAXBElement

-0.59

 فريبيس

-0.56

 AssemblyCompany

-0.56

SwingConstants

-0.54

berdayakan

-0.53

 {}));

-0.52

abetta

-0.51

POSITIVE LOGITS

 Minister

0.81

 minister

0.73

iramente

0.68

 ministres

0.67

minister

0.67

Minister

0.67

time

0.65

 suspect

0.63

minster

0.63

 MINISTER

0.62

Activations Density 0.117%

references to prime ministers and their roles

preceding "Minister" or "prime factors"

Prime Minister

No Comments

No Known Activations