INDEX

Explanations

key phrases that indicate actions, outcomes, or relationships in a context involving performance and evaluation

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

numbers and quantities

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

IntoConstraints

-0.41

нциклопедия

-0.38

InstrumentedTest

-0.37

本線

-0.37

Opéra

-0.36

ffilm

-0.35

}();

-0.34

 Normdatei

-0.33

 rodilla

-0.33

 considérons

-0.31

POSITIVE LOGITS

tableFuture

0.54

GEBURTSDATUM

0.51

tiful

0.50

uset

0.47

Према

0.46

nages

0.45

 transférez

0.44

VIAF

0.44

engu

0.44

eref

0.43

Activations Density 0.061%

key phrases that indicate actions, outcomes, or relationships in a context involving performance and evaluation

numbers and quantities

No Comments

No Known Activations