INDEX

Explanations

code-related keywords in kotlin relating to class structures, overriding and private scope

oai_token-act-pair · gemini-2.0-flash

text related to declarations or definitions in code

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

Foreign words

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

Metallic

-0.60

htë

-0.54

XmlType

-0.52

stasis

-0.51

ostatic

-0.51

 arşivlendi

-0.50

nościo

-0.48

WebControls

-0.48

WebServlet

-0.47

cèse

-0.47

POSITIVE LOGITS

 externi

0.64

 CreateTagHelper

0.59

Demografie

0.58

 ویکی‌پدی

0.57

 Partagez

0.55

 Biôgrafia

0.55

 صوتيه

0.53

المكان

0.52

 disambiguazione

0.52

 arabe

0.50

Activations Density 0.715%

code-related keywords in kotlin relating to class structures, overriding and private scope

text related to declarations or definitions in code

Foreign words

No Comments

No Known Activations