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

minist

-0.74

ITED

-0.71

McC

-0.69

Applications

-0.68

?????-

-0.67

Sov

-0.65

IBLE

-0.64

IAN

-0.63

 harmonic

-0.63

 Byzantine

-0.61

POSITIVE LOGITS

 redes

0.98

culosis

0.77

 ende

0.74

oway

0.72

ovember

0.70

ements

0.69

otin

0.69

zon

0.68

 este

0.65

regon

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.