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

nosis

-0.75

otaur

-0.73

 Canaver

-0.72

 Parables

-0.69

URA

-0.68

asonry

-0.67

xual

-0.65

flation

-0.64

ateurs

-0.64

nesota

-0.64

POSITIVE LOGITS

 Crosby

0.63

 resp

0.63

ocre

0.62

cht

0.61

akens

0.61

 unleash

0.60

win

0.58

ptr

0.56

Cu

0.56

Pod

0.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.