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

Negative Logits

ħĭ

-0.79

æ©Ł

-0.77

tsky

-0.71

 Webster

-0.69

ãĥĥãĥī

-0.68

fet

-0.68

LEASE

-0.67

¥µ

-0.66

orgetown

-0.66

ashington

-0.65

POSITIVE LOGITS

Å

0.72

 formations

0.70

hift

0.69

idth

0.68

isters

0.66

xia

0.66

cases

0.66

aunders

0.64

 Classes

0.63

 Concent

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.