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

piring

-0.73

ension

-0.71

iera

-0.68

ured

-0.66

 pineapple

-0.64

urous

-0.64

sword

-0.64

uring

-0.63

ensions

-0.63

 Chaser

-0.62

POSITIVE LOGITS

Ĥİ

0.99

cise

0.75

é¾įå¥ĳå£«

0.73

ropolitan

0.71

cept

0.70

×ĳ

0.69

Roaming

0.67

ILY

0.66

Internal

0.66

immune

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.