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

Negative Logits

egu

-0.74

 Nadu

-0.73

»Ĵ

-0.71

 Antar

-0.71

 tradem

-0.69

 Loans

-0.68

 keeper

-0.67

 administ

-0.65

 Moder

-0.65

 subsid

-0.64

POSITIVE LOGITS

blance

0.71

Connor

0.70

stru

0.70

ski

0.69

founded

0.69

WHERE

0.68

long

0.68

ise

0.67

glass

0.67

toe

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.