INDEX

Explanations

terms related to applications and their functionalities

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

app identification

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

XmlAccessType

-0.59

 propOrder

-0.59

Personendaten

-0.56

parsedMessage

-0.54

AndEndTag

-0.53

tė

-0.47

 surla

-0.47

 orgánico

-0.47

 CreateTagHelper

-0.46

 Italijani

-0.45

POSITIVE LOGITS

application

1.03

 Applications

1.02

 application

1.00

 applications

0.99

Applications

0.99

applications

0.97

 Application

0.94

Application

0.91

 Apps

0.90

apps

0.83

Activations Density 0.137%

terms related to applications and their functionalities

app identification

No Comments

No Known Activations