INDEX

Explanations

references to specific years or dates

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

The digit 0

np_acts-logits-general · gemini-2.0-flash

dates and years

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 autorytatywna

-0.91

 وتسجيلات

-0.84

 Cardinale

-0.75

]='\

-0.70

ResumeLayout

-0.68

>'+

-0.68

あります

-0.67

ParallelGroup

-0.66

 ostavi

-0.65

//

-0.65

POSITIVE LOGITS

1.24

 Nader

0.65

pellier

0.63

heses

0.62

jaciół

0.59

StoryboardSegue

0.59

 Torture

0.58

 Warner

0.57

 Ferrell

0.57

 Crock

0.56

Activations Density 0.072%

references to specific years or dates

The digit 0

dates and years

No Comments

No Known Activations