INDEX

Explanations

words and phrases related to cause and effect

oai_token-act-pair · gemini-2.0-flash

once

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 المعيارى

-0.67

XmlAccessorType

-0.59

rrggbb

-0.54

IUrlHelper

-0.53

tagHelper

-0.52

 typelib

-0.50

utor

-0.49

StringCopy

-0.49

nolia

-0.48

GEBURTSDATUM

-0.48

POSITIVE LOGITS

 once

3.31

once

2.95

Once

2.86

 Once

2.86

 ONCE

2.39

ONCE

2.30

一旦

1.74

 einmal

1.59

 Sobald

1.50

 sobald

1.45

Activations Density 3.204%

words and phrases related to cause and effect

once

No Comments

No Known Activations