INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 Occupations

-0.76

hend

-0.73

 Amen

-0.69

Sty

-0.69

als

-0.68

_-

-0.67

aspers

-0.67

 Zion

-0.65

 Surge

-0.64

se

-0.64

POSITIVE LOGITS

enegger

0.83

ename

0.82

ivery

0.77

etsk

0.72

 eject

0.70

ornia

0.69

iffs

0.68

zos

0.68

enhagen

0.67

accompan

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.