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

manship

-0.77

earchers

-0.67

enhagen

-0.65

 presumption

-0.63

 Description

-0.62

 Ging

-0.62

ocene

-0.62

verning

-0.61

soDeliveryDate

-0.60

 unbeliev

-0.60

POSITIVE LOGITS

jet

0.92

ooth

0.79

ridges

0.72

indust

0.71

izen

0.70

lear

0.68

etsy

0.66

tank

0.65

Indust

0.65

+(

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.