INDEX

Explanations

the occurrence of specific symbols or characters in the text that indicate sections of code or commands

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

</b>

-0.51

 lọc

-0.44

 esforço

-0.43

philo

-0.43

 workers

-0.43

/*

-0.43

Total

-0.43

 abusos

-0.43

 somos

-0.43

StructEnd

-0.42

POSITIVE LOGITS

 BoxDecoration

1.51

ParallelGroup

1.17

 Савезне

1.03

enumii

1.02

 StatelessWidget

0.93

 nahilalakip

0.93

InputBorder

0.93

 ویکی‌پدیا

0.91

 InputDecoration

0.86

 StatefulWidget

0.85

Activations Density 0.008%

the occurrence of specific symbols or characters in the text that indicate sections of code or commands

No Comments

No Known Activations