INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

halla

-0.80

 glim

-0.79

pse

-0.75

 volunt

-0.74

 advoc

-0.74

 enthusi

-0.74

 blat

-0.71

 unlaw

-0.69

 manslaughter

-0.68

jri

-0.68

POSITIVE LOGITS

 favorite

0.90

 favorites

0.86

 Favorite

0.78

favorite

0.74

fw

0.69

MAC

0.69

Cat

0.65

ãĥį

0.63

é»Ĵ

0.62

[_

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.