INDEX

Explanations

key terms and indicators related to data representation and analysis

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

numbers followed by of

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

-0.54

 '\\;'

-0.50

CloseOperation

-0.50

MemoryWarning

-0.50

 }}$}

-0.49

 utafitiHapana

-0.46

 المعيارى

-0.46

MLLoader

-0.45

]")]

-0.45

 AssemblyCulture

-0.44

POSITIVE LOGITS

beheer

0.47

tatuajes

0.47

 mxArray

0.46

 epä

0.45

enschutzer

0.45

charpe

0.43

 Accesorios

0.43

 määrä

0.42

 betyd

0.42

 Spuren

0.42

Activations Density 0.010%

key terms and indicators related to data representation and analysis

numbers followed by of

No Comments

No Known Activations