INDEX

Explanations

terms and variations related to security

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/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.20.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

 صوتيه

-0.91

uxxxx

-0.81

 CreateTagHelper

-0.77

AddTagHelper

-0.77

хьтан

-0.72

contentLoaded

-0.70

fjspx

-0.68

Jereo

-0.68

homonymie

-0.67

ArrowToggle

-0.67

POSITIVE LOGITS

 guards

0.62

 against

0.54

guarded

0.53

er

0.53

 guard

0.53

 Guards

0.51

 Security

0.50

men

0.50

 coussin

0.49

 Against

0.49

Activations Density 0.109%

terms and variations related to security

No Comments

No Known Activations