INDEX

Explanations

terms related to security and safety

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 Madd

-0.93

Vidite

-0.92

✨:

-0.91

tyfik

-0.89

 Roskov

-0.88

 newName

-0.86

SBATCH

-0.84

 виправивши

-0.83

ponents

-0.83

[+

-0.83

POSITIVE LOGITS

 security

1.24

 Security

1.18

 SECURITY

1.12

Secure

1.09

Security

1.08

er

1.07

SECURITY

1.02

Secured

1.01

 securities

1.01

security

1.01

Activations Density 0.073%

terms related to security and safety

No Comments

No Known Activations