INDEX

Explanations

code snippets and related terms from many programming languages as well as Latex.

oai_token-act-pair · gemini-2.0-flash

code-related syntax elements

np_token-act-pair-logits · gpt-4o-mini

code

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

prüche

-0.68

 ISNI

-0.62

simpleType

-0.61

 uska

-0.60

 perfons

-0.59

หวัด

-0.59

 betweenstory

-0.59

iffance

-0.58

 nahilalakip

-0.58

$_['

-0.58

POSITIVE LOGITS

__":

0.41

NamedQueries

0.40

__':

0.40

StoryboardSegue

0.40

iego

0.40

SpringBootTest

0.39

fej

0.37

 trasfer

0.37

idio

0.36

Activations Density 5.732%

code snippets and related terms from many programming languages as well as Latex.

code-related syntax elements

code

No Comments

No Known Activations