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

minist

-0.74

 hind

-0.73

estern

-0.69

ifference

-0.68

unction

-0.67

ependence

-0.66

alion

-0.63

geries

-0.61

 ordinance

-0.60

rued

-0.60

POSITIVE LOGITS

irez

0.84

é¾įå

0.70

Plex

0.67

å¤©

0.67

kins

0.66

ãģ®æ

0.64

KK

0.64

YP

0.63

éĸ

0.63

Medic

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.