INDEX

Explanations

references to specific job titles and employment-related terms

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

Dwight, office, employees

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

ImageContext

-0.47

Distribuzione

-0.43

Життєпис

-0.39

didSet

-0.35

Medidas

-0.35

 módulo

-0.35

Referencer

-0.34

 Disease

-0.34

 voulons

-0.33

disease

-0.33

POSITIVE LOGITS

 незавершена

0.56

########.

0.52

 kasarigan

0.50

 AspNetCore

0.49

HasAnnotation

0.48

EDEFAULT

0.46

ErrUnexpectedEOF

0.46

@[+][

0.45

fxml

0.44

 begr

0.44

Activations Density 0.112%

references to specific job titles and employment-related terms

Dwight, office, employees

No Comments

No Known Activations