INDEX

Explanations

words related to size and comparison

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

 size

-2.77

 Size

-2.55

size

-2.52

Size

-2.39

 SIZE

-2.33

 sizes

-2.30

sized

-2.14

 sized

-2.14

 Larger

-2.09

 Sizes

-2.03

POSITIVE LOGITS

 дописавши

0.54

AddHtmlAttribute

0.54

AndEndTag

0.52

<bos>

0.47

Czytaj

0.44

 ativar

0.42

TestingModule

0.42

MigrationBuilder

0.42

%">

0.41

 Puntos

0.41

Activations Density 3.458%

words related to size and comparison

foreign words

No Comments

No Known Activations