INDEX

Explanations

references to geopolitical entities and events involving Russia

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

出版年

-0.72

 године

-0.60

 --}}

-0.60

MLLoader

-0.58

abestanden

-0.58

 تانيه

-0.58

 Италијани

-0.58

IBarButtonItem

-0.57

aryen

-0.56

Personendaten

-0.53

POSITIVE LOGITS

 Russian

1.01

 Moscow

0.91

 Russia

0.91

 russian

0.91

 Fedor

0.89

Russian

0.86

 Rusia

0.85

 Russie

0.83

 Kremlin

0.83

 Russians

0.81

Activations Density 1.007%

references to geopolitical entities and events involving Russia

No Comments

No Known Activations