INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 Purg

-0.69

¬¼

-0.68

 Nasa

-0.66

aneously

-0.65

ACY

-0.62

 SELECT

-0.61

ICE

-0.59

 Atlantis

-0.59

 largeDownload

-0.59

 await

-0.58

POSITIVE LOGITS

dp

0.84

ippi

0.77

untled

0.76

itte

0.72

letcher

0.69

fam

0.69

doesn

0.67

olphin

0.67

alkyrie

0.66

 antioxid

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.