INDEX

Explanations

references to government investigations and intelligence briefings

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

Following investigative reports

np_acts-logits-general · gemini-2.0-flash

uncovering investigations and allegations

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

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

IsMutable

-0.92

ViewFeatures

-0.87

 ExecuteAsync

-0.82

RegistryLite

-0.79

SourceChecksum

-0.73

ArgsConstructor

-0.72

ftagPool

-0.71

 Италијани

-0.71

SBATCH

-0.70

 Мексичка

-0.70

POSITIVE LOGITS

 expose

1.71

 exposing

1.67

 revelations

1.58

 exposes

1.55

 exposé

1.53

 exposed

1.52

exposed

1.37

 uncovering

1.37

 revealing

1.35

 uncovered

1.33

Activations Density 0.498%

references to government investigations and intelligence briefings

Following investigative reports

uncovering investigations and allegations

No Comments

No Known Activations