INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

etc

-0.71

bits

-0.64

picture

-0.63

article

-0.61

terms

-0.60

 ..............

-0.60

 gauge

-0.57

 Picture

-0.57

uggest

-0.56

 charts

-0.56

POSITIVE LOGITS

alkyrie

0.70

issance

0.68

ailable

0.67

 dearly

0.64

olkien

0.64

vous

0.63

 graves

0.63

unia

0.62

AFTA

0.62

LR

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.