INDEX

Explanations

phrases conveying similarity or comparison

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

 normally

-0.54

="#"><

-0.51

DotNetBar

-0.50

yves

-0.49

fter

-0.47

ubourg

-0.46

 differently

-0.46

FXML

-0.46

 gereken

-0.46

achios

-0.46

POSITIVE LOGITS

 BoxFit

0.81

 minded

0.75

 виправивши

0.73

RectangleBorder

0.72

lihood

0.70

 circonstances

0.70

ParallelGroup

0.69

lity

0.67

 thereto

0.65

 görül

0.65

Activations Density 0.211%

phrases conveying similarity or comparison

No Comments

No Known Activations