INDEX

Explanations

references to identifiers and names in code or data structures

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

Keys, IDs, or names in code

np_acts-logits-general · gemini-2.0-flash

object identifiers, names, and keys

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 StatelessWidget

-0.82

 StatefulWidget

-0.72

MessageTagHelper

-0.53

цезда

-0.53

RefNanny

-0.53

 astore

-0.53

 mostaza

-0.52

ksiä

-0.51

 omkring

-0.51

 Bioaccumulative

-0.50

POSITIVE LOGITS

 ComVisible

0.64

 الاطلاع

0.61

Tembelea

0.57

FormUrlEncoded

0.55

GraphicsUnit

0.53

MessageState

0.52

DllImport

0.51

Personendaten

0.51

toCharArray

0.50

TestTools

0.50

Activations Density 0.366%

references to identifiers and names in code or data structures

Keys, IDs, or names in code

object identifiers, names, and keys

No Comments

No Known Activations