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

 Myst

-0.69

Pwr

-0.63

clair

-0.63

 Blair

-0.61

Peb

-0.60

 Hardy

-0.60

ipeg

-0.59

Lou

-0.59

 Celt

-0.58

 proble

-0.58

POSITIVE LOGITS

=-=-=-=-=-=-=-=-

0.86

kj

0.82

arious

0.75

ongo

0.74

heit

0.73

ttp

0.71

jon

0.71

hyde

0.71

bos

0.68

raq

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.