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

catentry

-0.79

 ratings

-0.75

 Chart

-0.72

IQ

-0.70

 Ratings

-0.69

antine

-0.65

PG

-0.64

ion

-0.62

CLUD

-0.61

Gem

-0.61

POSITIVE LOGITS

farious

0.91

civil

0.74

©¶æ

0.74

ilitarian

0.71

ignty

0.71

anchester

0.66

 gobl

0.65

intent

0.65

anship

0.65

bern

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.