INDEX

Explanations

code parts such as curly brackets and comments

oai_token-act-pair · gemini-2.0-flash

words related to programming or code structure

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

Code and programming

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

parsedMessage

-0.80

matchCondition

-0.61

stateProvider

-0.57

UrlResolution

-0.52

 Wikimedijinoj

-0.52

 مشارکت‌کنندگان

-0.52

✨:

-0.50

 ***!

-0.48

 ProtoMessage

-0.48

featureID

-0.47

POSITIVE LOGITS

Geplaatst

0.65

 Rapids

0.57

 Ababa

0.52

casio

0.52

enumi

0.51

 محفوظة

0.51

 besti

0.49

qrst

0.49

 developed

0.49

fortawesome

0.49

Activations Density 0.806%

code parts such as curly brackets and comments

words related to programming or code structure

Code and programming

No Comments

No Known Activations