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

iard

-0.73

 Antar

-0.66

 Duty

-0.66

umbn

-0.66

uci

-0.65

aurus

-0.65

 Archdemon

-0.65

 Antiqu

-0.63

essee

-0.63

throp

-0.63

POSITIVE LOGITS

igun

0.84

aired

0.74

Pak

0.72

ħĭ

0.69

wig

0.67

Plot

0.66

izoph

0.66

Preview

0.65

Spoiler

0.64

liga

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.