INDEX

Explanations

phrases indicating new product releases and updates

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

new releases and announcements

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

delwed

-0.54

maßen

-0.50

 Italijanski

-0.49

Personensuche

-0.49

msgTypes

-0.46

THISDAY

-0.44

postValue

-0.44

reactstrap

-0.43

oredCriteria

-0.43

 rowCount

-0.42

POSITIVE LOGITS

 latest

0.41

 debut

0.40

 terrific

0.40

Merkmale

0.39

 forthcoming

0.38

ftagPool

0.38

latest

0.38

 newest

0.37

ambilan

0.36

inaug

0.35

Activations Density 0.153%

phrases indicating new product releases and updates

new releases and announcements

No Comments

No Known Activations