INDEX

Explanations

phrases indicating problems or errors related to programming or software execution

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

Followed by an action taken by the user

np_acts-logits-general · gemini-2.0-flash

I/you do X

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

 Deixe

-0.55

Promise

-0.54

 AssemblyVersion

-0.52

madamente

-0.50

smarty

-0.49

ThemeOverlay

-0.49

Xna

-0.49

Serve

-0.49

Discuss

-0.49

)))));

-0.49

POSITIVE LOGITS

 disambiguazione

0.78

 manually

0.72

verwijspagina

0.67

曖昧さ回避

0.67

 accessed

0.66

 access

0.64

 input

0.63

 navigu

0.63

 navigate

0.62

Manually

0.62

Activations Density 0.602%

phrases indicating problems or errors related to programming or software execution

Followed by an action taken by the user

I/you do X

No Comments

No Known Activations