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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Suc

-0.77

Rai

-0.75

 Celest

-0.70

 Ples

-0.69

 Folk

-0.66

 Cree

-0.65

 Lust

-0.64

sters

-0.63

 Burg

-0.62

 Garg

-0.62

POSITIVE LOGITS

marks

0.76

ansk

0.74

rawdownloadcloneembedreportprint

0.73

rations

0.71

inders

0.68

bj

0.68

ocate

0.66

esson

0.65

 WATCHED

0.64

Article

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.