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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Dating

-0.81

 Skies

-0.76

 Drawn

-0.71

 Passenger

-0.70

SPONSORED

-0.68

Shot

-0.67

atown

-0.66

 Feet

-0.66

dd

-0.66

 Volunte

-0.65

POSITIVE LOGITS

arios

0.85

uti

0.73

',"

0.70

ollah

0.70

'."

0.68

ionic

0.67

"},

0.65

ymph

0.64

 incapac

0.64

ositories

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.