INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

imens

-1.08

abre

-0.79

 condol

-0.70

iesta

-0.68

.$

-0.66

 Centauri

-0.66

OTAL

-0.65

qqa

-0.65

 Destination

-0.65

andum

-0.64

POSITIVE LOGITS

manship

0.70

 oxid

0.68

eer

0.68

HAM

0.64

amac

0.63

ãĥŀ

0.63

pad

0.62

 ageing

0.60

Â¯Â¯Â¯Â¯

0.60

ping

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.