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

heed

-0.99

Closure

-0.91

issance

-0.91

Customer

-0.87

inse

-0.80

thood

-0.79

ilic

-0.78

qus

-0.75

merce

-0.74

-----------

-0.73

POSITIVE LOGITS

 nucleus

0.71

 seiz

0.69

 microphones

0.69

 skulls

0.68

 cort

0.68

 brains

0.66

 alarms

0.65

 Icar

0.65

 Bett

0.65

 veins

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.