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

 migrate

-0.76

 pige

-0.71

 bart

-0.68

thood

-0.67

 frogs

-0.64

 pubs

-0.64

 thou

-0.62

 ashore

-0.62

 crystal

-0.60

 poets

-0.59

POSITIVE LOGITS

 partName

0.80

FTA

0.79

arrison

0.72

ussion

0.70

alks

0.69

itably

0.67

allery

0.66

 Cosponsors

0.65

 Hamb

0.64

uther

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.