INDEX

Explanations

references to specific TV shows and creators, particularly in the context of humor and relationships

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

rom-coms, films, and TV shows

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

protoimpl

-0.53

thyst

-0.47

 Autorisations

-0.43

Begriffsklä

-0.40

ebbe

-0.40

 continúas

-0.40

FV

-0.39

 الحره

-0.39

 通販

-0.38

VersionUID

-0.38

POSITIVE LOGITS

XmlAccessType

0.46

GEBURTSDATUM

0.45

tanleria

0.45

 szóci

0.43

ourage

0.43

 /*#__

0.42

 صوتيه

0.41

 maternidade

0.39

ilosop

0.39

ayuno

0.39

Activations Density 0.089%

references to specific TV shows and creators, particularly in the context of humor and relationships

rom-coms, films, and TV shows

No Comments

No Known Activations