INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

oring

-0.71

Business

-0.67

olph

-0.66

 Wrestling

-0.65

brook

-0.64

oped

-0.64

gate

-0.63

 prostitutes

-0.63

 polic

-0.63

eur

-0.63

POSITIVE LOGITS

 discharge

0.70

 inacc

0.66

 initiate

0.64

HQ

0.62

iatus

0.62

Ì

0.61

Tea

0.60

 Salam

0.60

 signatures

0.59

 signature

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.