INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

ess

-0.68

 effected

-0.65

blind

-0.65

plain

-0.63

arted

-0.62

ass

-0.61

 psychiat

-0.60

asin

-0.59

 stret

-0.59

 compass

-0.59

POSITIVE LOGITS

Spread

0.81

 Edison

0.73

illac

0.71

SPA

0.70

ibaba

0.68

Son

0.68

venge

0.66

itol

0.64

Emb

0.64

INGTON

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.