INDEX

Explanations

clauses starting with "that" followed by a verb form of "to be"

oai_token-act-pair · gemini-2.0-flash

that

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

-0.60

and

-0.57

-0.48

or

-0.47

—

-0.46

-0.45

 which

-0.45

POSITIVE LOGITS

 تضيفلها

1.24

 незавершена

1.05

 Roskov

0.94

rungsseite

0.89

 Himo

0.87

SourceChecksum

0.84

 nahilalakip

0.84

intios

0.83

Diweddarwch

0.83

 linkovi

0.81

Activations Density 3.210%

clauses starting with "that" followed by a verb form of "to be"

that

No Comments

No Known Activations