INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

soType

-0.73

ends

-0.70

vertis

-0.65

liam

-0.64

 McKenna

-0.62

ĸļ

-0.61

McH

-0.60

assic

-0.60

aughtered

-0.60

soDeliveryDate

-0.59

POSITIVE LOGITS

 srfAttach

0.74

Catalog

0.71

arching

0.69

 conflic

0.68

ENTION

0.65

AMD

0.63

 retina

0.61

htaking

0.61

 pain

0.59

âĢİ

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.