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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

encers

-0.74

lishes

-0.73

iple

-0.72

 SPORTS

-0.71

 Andersen

-0.69

 Akron

-0.69

 Mehran

-0.68

elaide

-0.68

iciary

-0.67

foundland

-0.67

POSITIVE LOGITS

lus

0.70

que

0.65

 Strip

0.64

Wr

0.64

 sidel

0.64

ighed

0.64

Winged

0.62

Suggest

0.62

jected

0.62

 indign

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.