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

bda

-0.80

panic

-0.71

aminer

-0.70

uchi

-0.69

 Raider

-0.68

 Bomber

-0.63

 raft

-0.62

forge

-0.60

 Invaders

-0.60

gpu

-0.60

POSITIVE LOGITS

olves

0.74

MSN

0.73

utterstock

0.71

irable

0.70

ailability

0.70

idelines

0.69

irtual

0.66

Ó

0.65

 ARTICLE

0.64

 Rober

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.