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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

liction

-0.82

isoft

-0.81

tips

-0.81

bish

-0.78

ħĭ

-0.75

ratulations

-0.74

furt

-0.73

isks

-0.70

cipled

-0.70

eatures

-0.70

POSITIVE LOGITS

 apiece

0.70

 Dynam

0.68

 Olympia

0.68

 Gazette

0.68

 Lowell

0.67

 Mercury

0.65

 Venus

0.64

éĽ

0.64

asca

0.62

RT

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.