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

aila

-0.86

ucer

-0.77

stasy

-0.77

akespe

-0.71

soDeliveryDate

-0.71

SHIP

-0.70

ashtra

-0.70

ervation

-0.69

ividual

-0.68

rak

-0.67

POSITIVE LOGITS

 overse

0.74

Cob

0.69

Veh

0.68

 sprint

0.66

Hok

0.64

 embark

0.63

 Kaepernick

0.63

 priorit

0.62

Hog

0.62

 Palo

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.