INDEX

Explanations

words related to expressing personal opinions or directives

oai_token-act-pair · gemini-2.0-flash

presence of the word "is"

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

is

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

ConstraintMaker

-0.73

تقاوى

-0.69

 الحره

-0.63

RectangleBorder

-0.63

InjectAttribute

-0.63

 EconPapers

-0.62

IUrlHelper

-0.57

CodedInputStream

-0.57

KommentareTeilen

-0.52

siers

-0.52

POSITIVE LOGITS

is

1.99

Is

1.27

Is

1.11

is

0.96

are

0.85

的是

0.84

IS

0.84

 adalah

0.83

là

0.81

 است

0.80

Activations Density 4.294%

words related to expressing personal opinions or directives

presence of the word "is"

is

No Comments

No Known Activations