INDEX

Explanations

references to investigative reporting and official statements regarding incidents or controversies

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

ViewFeatures

-0.77

+#+#

-0.70

 satunya

-0.64

PreferredItem

-0.61

VersionUID

-0.59

 inimigos

-0.58

loroethane

-0.58

:✨

-0.58

EndProject

-0.57

 autres

-0.57

POSITIVE LOGITS

 police

0.75

 former

0.73

 President

0.72

US

0.67

 federal

0.66

 Senate

0.66

 Governor

0.66

 Former

0.64

 United

0.63

 Federal

0.62

Activations Density 0.329%

references to investigative reporting and official statements regarding incidents or controversies

No Comments

No Known Activations