INDEX

Explanations

terms and phrases related to security and privacy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

✨:

-0.98

SBATCH

-0.85

 виправивши

-0.84

expandindo

-0.83

Vidite

-0.82

 Madd

-0.79

 onPostExecute

-0.78

 newName

-0.78

tyfik

-0.78

[+

-0.77

POSITIVE LOGITS

 security

1.50

 Security

1.48

Security

1.38

 SECURITY

1.33

SECURITY

1.26

security

1.24

Secure

1.18

 securities

1.17

Secured

1.08

 secure

1.08

Activations Density 0.088%

terms and phrases related to security and privacy

No Comments

No Known Activations