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

recy

-0.85

hibited

-0.81

dies

-0.80

flu

-0.73

plus

-0.71

destruct

-0.71

 Died

-0.71

filled

-0.71

fab

-0.70

lied

-0.70

POSITIVE LOGITS

oras

0.72

 Koran

0.71

aimon

0.65

aples

0.65

ulz

0.63

ruit

0.61

ANGE

0.60

ander

0.60

 bible

0.59

ooting

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.