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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

DragonMagazine

-0.81

Rating

-0.71

morning

-0.70

lav

-0.70

æ©

-0.69

ifty

-0.68

rider

-0.68

rings

-0.66

rav

-0.64

¬¼

-0.64

POSITIVE LOGITS

DOI

0.73

Fas

0.72

 Morales

0.68

 Genie

0.67

 Reincarn

0.66

vae

0.65

 Monroe

0.64

 Bots

0.64

 Myers

0.63

CAN

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.