INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ded

-0.82

ready

-0.68

ten

-0.67

meet

-0.67

mer

-0.67

adal

-0.66

edd

-0.65

div

-0.65

pa

-0.65

Os

-0.65

POSITIVE LOGITS

£ı

0.95

ĻĤ

0.72

 filament

0.71

orsi

0.65

 helic

0.65

chnology

0.64

 Galile

0.63

 Thoughts

0.63

 Images

0.62

 hyster

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.