INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

velt

-0.87

ort

-0.78

vati

-0.73

intent

-0.72

Osw

-0.70

leans

-0.68

 skelet

-0.66

rising

-0.66

apore

-0.66

resso

-0.65

POSITIVE LOGITS

 silence

0.67

_>

0.67

=(

0.66

none

0.66

 Edition

0.65

 radius

0.60

 incomes

0.60

 impunity

0.59

²¾

0.59

 indist

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.