INDEX

Explanations

references to applications (apps) and associated terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

SourceChecksum

-1.04

parsedMessage

-0.87

Viited

-0.86

 nahilalakip

-0.86

"><?=

-0.78

--

-0.77

 JSTOR

-0.77

]")]

-0.77

 confronti

-0.77

 BorderSide

-0.76

POSITIVE LOGITS

app

1.64

App

1.53

 apps

1.46

App

1.45

APP

1.33

 Apps

1.28

app

1.28

getApp

1.28

APP

1.24

Apps

1.21

Activations Density 0.049%

references to applications (apps) and associated terms

No Comments

No Known Activations