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

 scaff

-0.71

 Samar

-0.70

ologne

-0.67

imore

-0.66

combe

-0.63

edin

-0.62

keleton

-0.62

 machinery

-0.61

onen

-0.61

 Swim

-0.61

POSITIVE LOGITS

cdn

0.76

ATA

0.71

orns

0.71

isa

0.71

bid

0.69

tro

0.69

attribute

0.67

åī

0.66

BC

0.64

IDS

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.