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

pire

-0.75

iru

-0.73

ãĤ³

-0.72

Loading

-0.71

cpu

-0.70

iphate

-0.70

ĸļ

-0.70

idan

-0.69

loader

-0.69

 Tornado

-0.68

POSITIVE LOGITS

 shenan

0.70

 practices

0.68

 Liver

0.67

 nomine

0.64

 redes

0.64

 noses

0.63

lasses

0.63

 blinded

0.62

 fellows

0.62

 crews

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.