INDEX

Explanations

specific terms and phrases related to social media and account management

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.36.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

WebElementEntity

-0.77

Personendaten

-0.60

AddTagHelper

-0.57

 &___

-0.57

VersionUID

-0.53

 surla

-0.53

fortawesome

-0.53

#+#

-0.52

MENAFN

-0.52

AsUp

-0.52

POSITIVE LOGITS

nya

0.49

ם

0.49

ๆ

0.45

то

0.43

ς

0.41

ssa

0.41

ו

0.41

里

0.40

로

0.39

ly

0.37

Activations Density 0.130%

specific terms and phrases related to social media and account management

No Comments

No Known Activations