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

 Ribbon

-0.74

 Registry

-0.73

 Bluetooth

-0.69

 Onion

-0.66

 Herb

-0.63

 inventory

-0.61

 registry

-0.61

 Siberian

-0.61

IoT

-0.61

 ledger

-0.59

POSITIVE LOGITS

cakes

0.77

acan

0.71

©¶æ

0.65

uca

0.65

culus

0.64

Ã§a

0.64

neg

0.63

amaz

0.63

Synopsis

0.63

argument

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.