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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ilipp

-0.80

hub

-0.70

Ŀ

-0.69

 WATCHED

-0.68

gans

-0.65

zz

-0.63

ATURES

-0.63

athing

-0.62

oses

-0.62

hei

-0.62

POSITIVE LOGITS

soDeliveryDate

0.77

.)

0.74

rue

0.70

 Allaah

0.66

ouble

0.66

oggles

0.66

rial

0.64

prints

0.64

bps

0.63

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.