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

SourceFile

-0.70

interrupted

-0.67

 frequ

-0.64

iage

-0.63

dale

-0.63

OWS

-0.62

Vis

-0.62

 pilgr

-0.61

 idle

-0.61

NAS

-0.60

POSITIVE LOGITS

arnaev

0.73

veland

0.67

 manifesto

0.65

grand

0.64

Chapter

0.64

 thumbnail

0.61

athering

0.60

lator

0.60

 Spiegel

0.59

 spoiler

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.