INDEX

Explanations

words or phrases that refer to restrictions and order in society, or lines of people.

oai_token-act-pair · gemini-2.0-flash

crowds and lines

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

WithIOException

-0.70

Попис

-0.62

出版年

-0.61

 intercal

-0.60

 оригіналу

-0.60

aroa

-0.56

multicolumn

-0.55

 pylint

-0.55

utches

-0.54

Šaltiniai

-0.54

POSITIVE LOGITS

%")

0.57

<bos>

0.56

 crowd

0.54

 européennes

0.52

 crowds

0.52

 doprav

0.52

__':

0.51

 throng

0.51

tł

0.50

 crowding

0.49

Activations Density 0.688%

words or phrases that refer to restrictions and order in society, or lines of people.

crowds and lines

No Comments

No Known Activations