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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

akedown

-0.72

heim

-0.68

quest

-0.65

 Cummings

-0.65

 Borough

-0.64

vern

-0.63

McH

-0.63

iren

-0.63

µ

-0.62

combe

-0.62

POSITIVE LOGITS

sed

0.69

 scissors

0.68

ONSORED

0.67

Accessory

0.63

 Valid

0.62

 stamps

0.61

 Sharing

0.61

 snag

0.60

idable

0.60

icable

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.