INDEX

Explanations

references to nieces and nephews

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

niece or nieces

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

WindowConstants

-0.50

 Energ

-0.47

}();

-0.46

providedIn

-0.46

},'

-0.45

endphp

-0.43

//*/

-0.43

KommentareTeilen

-0.43

Symbol

-0.43

 Targ

-0.43

POSITIVE LOGITS

 nieces

0.89

 niece

0.66

 nephews

0.57

 Schwester

0.54

 sisters

0.52

 frère

0.51

 Masalah

0.51

 brothers

0.50

findpost

0.50

 sorella

0.47

Activations Density 0.000%

references to nieces and nephews

niece or nieces

No Comments

No Known Activations