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

enegger

-0.78

-0.72

nikov

-0.71

PRES

-0.69

fman

-0.67

EVA

-0.67

tex

-0.66

Mi

-0.66

ÃŁ

-0.65

uble

-0.63

POSITIVE LOGITS

PLA

0.74

 begs

0.67

 repl

0.66

 contextual

0.64

 replacements

0.64

 google

0.63

 assigns

0.62

isco

0.62

eer

0.62

 contempor

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.