INDEX

Explanations

words and phrases related to civil unrest and violence, especially in an international context

oai_token-act-pair · gemini-2.0-flash

large quantities of people or law enforcement

np_token-act-pair-logits · gpt-4o-mini

Hundreds, thousands, millions

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 antaranya

-0.60

antaranya

-0.56

ifrance

-0.56

 referrerpolicy

-0.54

✨:

-0.50

 vVar

-0.50

 mergeFrom

-0.50

harapkan

-0.50

Inhalt

-0.49

డు

-0.48

POSITIVE LOGITS

 hundreds

0.91

ⓧ

0.90

hundreds

0.81

 thousands

0.81

 police

0.75

 dozens

0.74

Hundreds

0.74

thousands

0.71

 millions

0.71

 Police

0.70

Activations Density 3.249%

words and phrases related to civil unrest and violence, especially in an international context

large quantities of people or law enforcement

Hundreds, thousands, millions

No Comments

No Known Activations