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

hander

-0.80

 convent

-0.70

soDeliveryDate

-0.66

icum

-0.65

ne

-0.65

nton

-0.63

 rudimentary

-0.63

 playbook

-0.62

bourg

-0.62

 cunt

-0.60

POSITIVE LOGITS

ï¸

0.82

âĺ

0.72

wcs

0.68

EE

0.67

alogue

0.65

 DRAG

0.65

wal

0.64

live

0.62

codes

0.62

 Ratings

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.