INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

STEM

-0.79

advertisement

-0.71

URRENT

-0.67

keeping

-0.66

ãĤ©

-0.65

current

-0.65

SO

-0.65

MIT

-0.63

TAIN

-0.63

 bearings

-0.62

POSITIVE LOGITS

asio

0.75

ierre

0.68

 Marcos

0.66

gypt

0.63

ourke

0.61

 compliment

0.60

 condem

0.59

iera

0.59

 communism

0.59

eur

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.