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

 Parables

-0.64

oresc

-0.64

atti

-0.63

dain

-0.63

umbn

-0.62

Ã¨re

-0.62

 Bake

-0.61

itu

-0.60

 baskets

-0.60

oult

-0.59

POSITIVE LOGITS

cember

0.76

 snail

0.70

afia

0.70

Wall

0.69

mails

0.64

adel

0.63

 paran

0.63

uthor

0.63

ompl

0.62

elist

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.