INDEX

Explanations

references to data formats and listings

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

json and version numbers

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

ThroughAttribute

-0.74

GEBURTS

-0.61

OGND

-0.56

Vidite

-0.56

featureID

-0.52

олові

-0.51

kijken

-0.51

المشاركات

-0.48

wpi

-0.47

 مرئيه

-0.47

POSITIVE LOGITS

 defStyleAttr

0.39

està

0.39

 StatelessWidget

0.38

RequiresApi

0.38

VersionUID

0.36

plain

0.34

withOpacity

0.34

pgsql

0.33

 Serif

0.33

 CURIAM

0.33

Activations Density 0.000%

references to data formats and listings

json and version numbers

No Comments

No Known Activations