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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Jordanian

-0.68

enei

-0.66

 lubric

-0.66

 fung

-0.66

alore

-0.65

 Genie

-0.65

 restored

-0.63

 Oman

-0.63

 Brune

-0.62

reen

-0.61

POSITIVE LOGITS

vised

0.69

itled

0.67

illet

0.63

quad

0.62

cheat

0.62

 Atkinson

0.62

ledged

0.61

dx

0.60

entary

0.60

ciples

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.