INDEX

Explanations

words related to ancient history

oai_token-act-pair · gemini-2.0-flash

Ancient civilizations/history

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 myſelf

-1.05

 itſelf

-1.01

 iſt

-0.94

 ſeveral

-0.94

 Monfieur

-0.92

 purpoſe

-0.91

Eſ

-0.90

 Jefus

-0.89

 Reſ

-0.88

 houſe

-0.87

POSITIVE LOGITS

 material

0.46

 createState

0.46

0.44

Se

0.44

JAXB

0.43

 numerus

0.43

 Hung

0.42

Ar

0.41

se

0.41

Activations Density 2.972%

words related to ancient history

Ancient civilizations/history

No Comments

No Known Activations