INDEX

Explanations

the beginning of new sections or topics in a text

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

risk of exposure

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.16.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

Hentet

-0.74

Hauptartikel

-0.69

 Wirkung

-0.62

 FBref

-0.57

</tfoot>

-0.56

basicConfig

-0.54

UnitTesting

-0.54

 kvalit

-0.53

ativement

-0.53

saraba

-0.53

POSITIVE LOGITS

 vulnerable

0.85

 exposed

0.84

 typelib

0.72

 Vulnerable

0.70

 Exposed

0.69

 unprotected

0.68

 exposing

0.66

 exposes

0.66

 expose

0.65

 exposure

0.63

Activations Density 0.248%

the beginning of new sections or topics in a text

risk of exposure

No Comments

No Known Activations