INDEX

Explanations

numerical data and statistical information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

Personendaten

-0.57

новништво

-0.56

 initComponents

-0.52

 препратки

-0.52

 Normdatei

-0.52

oredCriteria

-0.50

 мәкал

-0.50

GeoNames

-0.49

 protoimpl

-0.48

awtextra

-0.47

POSITIVE LOGITS

Forty

0.47

 Sixty

0.47

 Forty

0.45

Sixty

0.44

Thirty

0.43

 Seventy

0.43

forty

0.42

 Thirty

0.41

tieth

0.40

 Boven

0.40

Activations Density 1.461%

numerical data and statistical information

No Comments

No Known Activations