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

 Mortal

-0.66

 Replay

-0.65

 Hide

-0.64

',"

-0.64

 Blaz

-0.64

æľ

-0.64

âĦ¢:

-0.63

aceous

-0.63

Yad

-0.61

horse

-0.61

POSITIVE LOGITS

brance

1.08

ovie

0.83

otics

0.79

undown

0.76

estern

0.72

ramer

0.72

atech

0.70

owler

0.70

Dialogue

0.70

 sshd

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.