INDEX

Explanations

references to historical Islamic political and religious factions

oai_token-act-pair · gemini-2.0-flash

words that might indicate conflict or sectarian divisions

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

history

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

GraphicsUnit

-0.77

 nakalista

-0.71

 Référence

-0.68

 camp

-0.67

GEBURTS

-0.65

Datuak

-0.64

oneofs

-0.64

Portail

-0.64

UnusedPrivate

-0.64

GeneratedMessage

-0.63

POSITIVE LOGITS

saraba

0.61

олові

0.46

itteet

0.46

 Pharisees

0.46

 here

0.44

اده

0.44

FormTagHelper

0.43

here

0.43

DispatchToProps

0.42

memcmp

0.42

Activations Density 0.788%

references to historical Islamic political and religious factions

words that might indicate conflict or sectarian divisions

history

No Comments

No Known Activations