INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

STEM

-0.75

MH

-0.71

lies

-0.67

ç¥ŀ

-0.65

Interested

-0.65

 livest

-0.64

mA

-0.63

Tel

-0.63

Quant

-0.63

Unity

-0.63

POSITIVE LOGITS

 Court

1.54

 COURT

0.95

 court

0.89

Ct

0.81

his

0.76

Court

0.74

ertodd

0.73

 body

0.72

court

0.71

ichick

0.70

Activations Density 0.000%

No Known Activations

This feature has no known activations.