INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

aucus

-0.76

DonaldTrump

-0.71

 endif

-0.68

osponsors

-0.66

rimp

-0.65

agascar

-0.63

otine

-0.63

 precaution

-0.63

ourning

-0.63

orer

-0.62

POSITIVE LOGITS

æ©

0.66

verts

0.64

atis

0.64

xes

0.63

ensional

0.62

ÃŃa

0.61

stairs

0.60

 ROCK

0.60

sten

0.59

FIN

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.