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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Accounting

-0.67

INO

-0.65

odcast

-0.65

 footing

-0.64

 srfAttach

-0.63

 guiName

-0.62

 Titanium

-0.61

ovember

-0.60

 Complex

-0.59

RED

-0.59

POSITIVE LOGITS

lio

0.76

catentry

0.72

esson

0.69

una

0.66

alus

0.66

Minor

0.64

ourt

0.64

 imitation

0.63

Il

0.63

iel

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.