INDEX

Explanations

phrases that include time, rates, measurement, and the word "very".

oai_token-act-pair · gemini-2.0-flash

amounts of time

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

Efq

-1.26

 myſelf

-1.16

+#+#

-1.14

 itſelf

-1.11

 himſelf

-1.05

 Theſe

-1.04

 ―――――

-1.03

 Monfieur

-1.03

 iſt

-1.02

^(@)

-1.02

POSITIVE LOGITS

 several

1.22

 years

1.20

 many

1.05

 multiple

0.96

 decades

0.96

several

0.95

 months

0.86

 Several

0.85

Several

0.84

 numerous

0.83

Activations Density 4.871%

phrases that include time, rates, measurement, and the word "very".

amounts of time

No Comments

No Known Activations