INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

etheless

-0.80

endas

-0.78

istar

-0.72

 tion

-0.70

¥ŀ

-0.66

srf

-0.65

 Nicol

-0.64

igans

-0.64

 Santiago

-0.63

archy

-0.63

POSITIVE LOGITS

opath

0.73

OTAL

0.68

Ð¾

0.67

âĵĺ

0.67

uten

0.67

 chromosome

0.66

UCK

0.65

%%%%

0.64

Û

0.64

OUGH

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.