INDEX

Explanations

structured data related to assembly attributes and licensing information

oai_token-act-pair · gpt-4o-mini Triggered by @bot

Code, configurations, and imports

np_acts-logits-general · gemini-2.0-flash

code constructs like `import`

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 hant

-0.46

iter

-0.45

BL

-0.44

ya

-0.43

lay

-0.43

 cristi

-0.43

("~/

-0.42

冶

-0.42

 navideñas

-0.42

笑道

-0.41

POSITIVE LOGITS

InjectAttribute

1.01

expandindo

0.99

findpost

0.98

 nahilalakip

0.86

 متعلقه

0.85

 EconPapers

0.83

 Signalez

0.82

Autoritní

0.81

 lenker

0.80

forRoot

0.80

Activations Density 0.033%

structured data related to assembly attributes and licensing information

Code, configurations, and imports

code constructs like `import`

No Comments

No Known Activations