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

framework

-0.83

osi

-0.81

gif

-0.80

ecd

-0.75

Aust

-0.71

align

-0.71

assad

-0.69

adoes

-0.68

bul

-0.67

reply

-0.67

POSITIVE LOGITS

 Beir

0.90

 Wilmington

0.76

 Bounty

0.74

 Pond

0.72

 Staten

0.71

 Bucks

0.70

 Courage

0.70

 Organ

0.69

 Volunteers

0.69

 Penal

0.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.