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

Sho

-0.84

 deleg

-0.76

BY

-0.62

 Fallon

-0.62

anes

-0.61

 laps

-0.60

Nap

-0.59

 delegates

-0.59

 Eleven

-0.58

 Indy

-0.57

POSITIVE LOGITS

 opio

0.74

merce

0.68

erker

0.67

noxious

0.67

ĨĴ

0.66

humane

0.65

 shelter

0.63

hiro

0.63

ettle

0.62

 metic

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.