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

esis

-0.74

nard

-0.71

ord

-0.70

ety

-0.70

sylvania

-0.69

sand

-0.68

redo

-0.66

aos

-0.66

onding

-0.66

atial

-0.66

POSITIVE LOGITS

 nuns

0.73

advertising

0.69

 unborn

0.69

Bey

0.66

 orphans

0.63

 spoilers

0.63

 Scully

0.62

uning

0.61

assad

0.61

Catalog

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.