INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 recall

-0.69

 bully

-0.66

 decide

-0.65

 fibre

-0.65

 bothered

-0.65

 organising

-0.63

¡

-0.63

 Able

-0.63

 sponsoring

-0.62

 Docker

-0.62

POSITIVE LOGITS

pour

0.80

tesque

0.77

OAD

0.72

Pry

0.72

fty

0.71

hib

0.71

itri

0.69

ãģĤ

0.68

igun

0.68

MU

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.