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

ateurs

-0.73

hops

-0.70

 Indy

-0.67

 Darrell

-0.66

alogue

-0.66

Ð½

-0.64

oeuv

-0.64

 Discipline

-0.64

 Chomsky

-0.63

 Dispatch

-0.63

POSITIVE LOGITS

comed

0.81

robe

0.74

rome

0.69

 express

0.69

Beaut

0.68

ench

0.67

beaut

0.66

 manic

0.66

yout

0.65

asking

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.