INDEX

Explanations

instances where the author is trying to assist the reader and telling them what they need to do

oai_token-act-pair · gemini-2.0-flash

foreign words

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

DockStyle

-0.72

MigrationBuilder

-0.70

rrggbb

-0.65

stridium

-0.63

 CreateTagHelper

-0.62

ksikon

-0.61

ClientRect

-0.58

tableFuture

-0.57

存于互联网档案馆

-0.55

itettura

-0.55

POSITIVE LOGITS

 الحره

0.51

 المعيارى

0.44

Millisecond

0.42

فاض

0.42

bps

0.42

 Yani

0.42

 Inferior

0.42

 vola

0.41

Zdroje

0.40

Activations Density 5.779%

instances where the author is trying to assist the reader and telling them what they need to do

foreign words

No Comments

No Known Activations