INDEX

Explanations

references to units of time like "weeks", "days", "years" and the word "time" itself

oai_token-act-pair · gemini-2.0-flash

until

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

OwnProperty

-0.48

 chêne

-0.45

void

-0.45

kadi

-0.41

bastien

-0.41

انات

-0.40

انة

-0.40

пря

-0.40

اند

-0.39

 void

-0.39

POSITIVE LOGITS

 until

1.53

until

1.37

Until

1.31

 till

1.30

 Until

1.30

 UNTIL

1.29

 untill

1.27

 TILL

1.16

Till

1.16

 Till

1.16

Activations Density 1.851%

references to units of time like "weeks", "days", "years" and the word "time" itself

until

No Comments

No Known Activations