INDEX

Explanations

numerical data and statistics related to health metrics

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 eleven

-0.41

ten

-0.36

 Eleven

-0.35

eleven

-0.33

ten

-0.33

 Twelve

-0.33

Eleven

-0.31

 Eleventh

-0.31

 сло

-0.31

十二

-0.29

POSITIVE LOGITS

 ſehr

0.83

 ſeinen

0.81

 ſeiner

0.81

 ſeine

0.80

<unused16>

0.80

<unused52>

0.80

<unused68>

0.80

 ſeinem

0.80

<pad>

0.80

<unused3>

0.79

Activations Density 0.515%

numerical data and statistics related to health metrics

No Comments

No Known Activations