INDEX

Explanations

phrases related to security and privacy measures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

MLLoader

-0.61

 onData

-0.52

libft

-0.48

 wireType

-0.46

 comuniques

-0.45

 StringTokenizer

-0.45

InsertCommand

-0.45

󠁢

-0.45

\{\\

-0.44

msgTypes

-0.44

POSITIVE LOGITS

 protection

1.13

 security

1.05

 protecting

0.97

protection

0.94

 protective

0.94

 protect

0.93

security

0.93

Security

0.90

 Protection

0.90

 Security

0.90

Activations Density 0.901%

phrases related to security and privacy measures

No Comments

No Known Activations