INDEX

Explanations

references to security-related concepts and issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

✨:

-0.98

Vidite

-0.98

tyfik

-0.96

 Madd

-0.90

 Murch

-0.85

 Leafs

-0.85

 Payable

-0.81

WebVitals

-0.81

WithMany

-0.80

 виправивши

-0.80

POSITIVE LOGITS

 security

1.31

 Security

1.26

Security

1.18

 SECURITY

1.12

security

1.07

SECURITY

1.04

 securities

1.03

Secure

0.99

er

0.98

Secured

0.92

Activations Density 0.065%

references to security-related concepts and issues

No Comments

No Known Activations