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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rival

-0.71

 clipboard

-0.67

mson

-0.67

indal

-0.67

anton

-0.63

regor

-0.62

uner

-0.62

fer

-0.62

ayne

-0.62

wild

-0.61

POSITIVE LOGITS

 Cheong

0.93

 Marketable

0.91

 IMAGES

0.81

oglu

0.71

uzzle

0.69

xual

0.68

 Nicola

0.65

 Euros

0.61

IOC

0.61

ãĤ§

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.