INDEX

Explanations

phrases related to protection and safeguarding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

SequentialGroup

-0.57

 мәгълү

-0.53

 Wikiseite

-0.50

+#+

-0.50

 bedrijf

-0.49

nsito

-0.48

yarnpkg

-0.48

windowFixed

-0.47

 createdBy

-0.47

 mixer

-0.47

POSITIVE LOGITS

 protect

1.70

 protection

1.63

protect

1.59

 Protect

1.56

 protecting

1.53

 protects

1.52

 Protection

1.50

 PROTECT

1.48

Protect

1.48

protection

1.47

Activations Density 0.146%

phrases related to protection and safeguarding

No Comments

No Known Activations