INDEX

Explanations

descriptions of user-friendly software and interfaces

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

"User" followed by a management-related term

np_acts-logits-general · gemini-2.0-flash

user interface and experience

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 Wicidata

-0.61

 BoxDecoration

-0.59

DockStyle

-0.59

GEBURTSDATUM

-0.59

šanai

-0.56

ExtendWith

-0.55

mito

-0.54

 متعلقه

-0.54

最快更新

-0.53

 AspNetCore

-0.53

POSITIVE LOGITS

 interface

2.03

 interfaces

1.65

interface

1.60

 Interface

1.57

UI

1.55

 интерфей

1.55

 interfaz

1.52

GUI

1.49

 user

1.46

Interface

1.45

Activations Density 0.365%

descriptions of user-friendly software and interfaces

"User" followed by a management-related term

user interface and experience

No Comments

No Known Activations