INDEX

Explanations

mentions of the application content type in various contexts

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

application media types

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

 propOrder

-0.79

 ✭✭

-0.57

Tikang

-0.52

elemField

-0.51

 mergeFrom

-0.50

oneofs

-0.50

 виправивши

-0.48

withIdentifier

-0.48

BindView

-0.47

 onResponse

-0.47

POSITIVE LOGITS

application

1.41

 application

1.16

 Application

0.99

APPLICATION

0.93

Application

0.92

 APPLICATION

0.90

 aplicación

0.88

 applications

0.85

applications

0.82

 Applications

0.82

Activations Density 0.002%

mentions of the application content type in various contexts

application media types

No Comments

No Known Activations