INDEX

Explanations

references to programming structures or components, particularly in the context of code or libraries

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

"util" or "apache" within code-related texts

np_acts-logits-general · gemini-2.0-flash

apache commons math

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

featureID

-0.75

GEBURTSDATUM

-0.71

 OFDb

-0.70

yarnpkg

-0.68

 kaarangay

-0.65

Personendaten

-0.63

 Biôgrafia

-0.62

 typelib

-0.61

 ویکی‌پدی

-0.61

 Italijanski

-0.61

POSITIVE LOGITS

’

0.41

mathrm

0.40

 visuel

0.37

begin

0.36

Làm

0.33

 efic

0.32

 pacient

0.32

做得

0.32

 Agencia

0.32

Activations Density 0.049%

references to programming structures or components, particularly in the context of code or libraries

"util" or "apache" within code-related texts

apache commons math

No Comments

No Known Activations