INDEX

Explanations

phrases and terminology related to statistical data or analyses

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100

Prompts (Dashboard)

24,576 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

 يتيمه

-0.56

gebob

-0.53

Personendaten

-0.50

 nejak

-0.48

adakan

-0.48

følgelig

-0.47

insegna

-0.45

 AppCompat

-0.45

hæng

-0.45

 felicità

-0.44

POSITIVE LOGITS

 million

0.64

ScopeManager

0.60

 Million

0.58

 millions

0.55

 thousand

0.55

一千

0.54

Million

0.54

 MILLION

0.53

 billion

0.52

 milion

0.52

Activations Density 0.135%

phrases and terminology related to statistical data or analyses

No Comments

No Known Activations