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

 spons

-0.75

 caut

-0.75

 appre

-0.74

apons

-0.72

staking

-0.70

 predec

-0.70

 cryptoc

-0.69

 ageing

-0.68

 sugg

-0.68

 conclud

-0.68

POSITIVE LOGITS

urized

0.67

PLIED

0.66

isphere

0.65

 Whitman

0.64

Sean

0.64

ories

0.64

 Lens

0.63

recated

0.63

 Restore

0.63

 Shots

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.