INDEX

Explanations

code related to user information handling, such as names and avatars

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.34.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

 surla

-0.71

httphttps

-0.57

VersionUID

-0.55

<?

-0.46

AutoModerator

-0.46

uxxxx

-0.45

RenderAtEndOf

-0.45

 CanadaChoose

-0.44

providedIn

-0.44

 CURIAM

-0.44

POSITIVE LOGITS

󠁴

0.42

ruik

0.42

 GenerationType

0.41

 Jaffe

0.40

 handlar

0.40

atguigu

0.39

⤹

0.38

 lenker

0.37

儿

0.37

 Emits

0.36

Activations Density 0.081%

code related to user information handling, such as names and avatars

No Comments

No Known Activations