INDEX

Explanations

positions or locations within a graphical user interface or layout

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

 Ahead

-0.63

ỡng

-0.60

 تانيه

-0.59

 محفوظة

-0.58

Ahead

-0.57

 كومونز

-0.57

 ahead

-0.57

 cherchés

-0.52

WebVitals

-0.51

ISupport

-0.51

POSITIVE LOGITS

 corner

2.01

corner

1.69

 corners

1.62

 Corner

1.55

Corner

1.53

 CORNER

1.43

 esquina

1.42

 Corners

1.32

corners

1.29

 Ecke

1.24

Activations Density 0.125%

positions or locations within a graphical user interface or layout

No Comments

No Known Activations