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

ĵĺ

-0.70

 Tayyip

-0.67

Yel

-0.67

Kyr

-0.66

ople

-0.66

Sus

-0.64

Vil

-0.64

 witnesses

-0.63

 punct

-0.62

 Rasmussen

-0.62

POSITIVE LOGITS

issance

0.92

quickShipAvailable

0.80

QB

0.80

DX

0.80

vana

0.73

Today

0.68

vP

0.67

leans

0.67

dq

0.67

lance

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.