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

ocial

-0.71

actionDate

-0.69

assic

-0.64

 referen

-0.63

 moder

-0.59

 suites

-0.59

 antioxid

-0.58

atorial

-0.57

 Charter

-0.57

uay

-0.57

POSITIVE LOGITS

 Nadu

0.74

acteria

0.74

 ILCS

0.71

oin

0.69

olo

0.69

iop

0.68

lde

0.68

terday

0.67

onse

0.66

ouched

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.