INDEX

Explanations

prepositions and connections that indicate relationships in the text

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

"to" followed by a verb

np_acts-logits-general · gemini-2.0-flash

to followed by verbs or articles

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

contentLoaded

-0.82

AsUp

-0.67

 صوتيه

-0.67

farwyddwr

-0.64

 UnityEditor

-0.64

 Exactos

-0.64

matchCondition

-0.62

 MenuView

-0.62

 geworden

-0.62

windowFixed

-0.60

POSITIVE LOGITS

the

0.69

//});

0.67

]--;

0.60

//};

0.59

//}

0.58

put

0.56

__',

0.55

mpion

0.54

 các

0.54

*)&

0.52

Activations Density 0.925%

prepositions and connections that indicate relationships in the text

"to" followed by a verb

to followed by verbs or articles

No Comments

No Known Activations