INDEX

Explanations

the term "main" in various contexts

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

The token "Main" followed by certain words

np_acts-logits-general · gemini-2.0-flash

main menu, target, navigation, memo

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

UnknownFields

-0.67

aarrggbb

-0.67

 AssemblyCompany

-0.62

 дописавши

-0.62

ówno

-0.61

VersionUID

-0.58

matchCondition

-0.58

дзе

-0.57

 okuyayım

-0.56

numerusform

-0.56

POSITIVE LOGITS

 Main

1.00

tainer

0.99

tains

0.95

stays

0.95

 MAIN

0.92

 main

0.89

frame

0.83

Main

0.82

tainers

0.79

MAIN

0.76

Activations Density 0.112%

the term "main" in various contexts

The token "Main" followed by certain words

main menu, target, navigation, memo

No Comments

No Known Activations