INDEX

Explanations

terms related to nuclear energy and weaponry

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/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.9.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

 defaultstate

-0.93

Vidite

-0.87

knapp

-0.77

 refusé

-0.75

 contemporaine

-0.73

 Visconti

-0.70

 Viceroy

-0.69

SuppressMessage

-0.69

شهاد

-0.68

 disparu

-0.67

POSITIVE LOGITS

 nuclear

1.61

nuclear

1.44

 Nuclear

1.40

Nuclear

1.34

 NUCLEAR

1.24

uclear

1.21

 nuclei

1.08

 nucléaire

1.07

 nukes

1.01

 atomic

0.98

Activations Density 0.094%

terms related to nuclear energy and weaponry

No Comments

No Known Activations