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

idden

-0.72

aths

-0.66

IT

-0.65

ĸļ

-0.64

present

-0.64

âĢ¢âĢ¢

-0.63

 sche

-0.62

conservancy

-0.61

¶æ

-0.61

 oath

-0.61

POSITIVE LOGITS

 Lowell

0.76

 Paste

0.74

emis

0.73

illary

0.72

achu

0.68

rament

0.68

itol

0.68

lla

0.66

eva

0.65

trak

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.