INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

amental

-0.78

tarian

-0.71

 invari

-0.70

 differential

-0.69

estern

-0.68

tarians

-0.67

ARI

-0.66

odynam

-0.65

Reviewer

-0.64

 Seym

-0.64

POSITIVE LOGITS

 realise

0.75

 Butcher

0.65

 surely

0.63

>>>>>>>>

0.59

 Next

0.58

 Bravo

0.57

Ùħ

0.57

 ultimately

0.57

andro

0.56

 sadly

0.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.