INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

mand

-0.79

recomm

-0.74

 Theft

-0.71

imore

-0.69

 delinqu

-0.63

anyl

-0.63

 plurality

-0.63

pard

-0.62

 Prohibition

-0.62

 complying

-0.62

POSITIVE LOGITS

aldo

0.82

anto

0.72

ItemTracker

0.71

 Krugman

0.70

oker

0.68

icio

0.67

wagon

0.67

vp

0.67

okers

0.66

ivia

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.