INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

missions

-0.78

cano

-0.78

 Publication

-0.74

mission

-0.72

ocese

-0.70

mitted

-0.69

xxxxxxxx

-0.68

ropri

-0.66

mail

-0.66

handled

-0.66

POSITIVE LOGITS

 Nickel

0.85

tun

0.69

ÙĴ

0.63

Rib

0.63

 Mold

0.63

 Krypt

0.62

Nit

0.61

 Balk

0.60

 peac

0.60

 sulf

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.