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

uled

-0.75

WT

-0.71

chy

-0.66

inery

-0.66

ngth

-0.65

 democr

-0.65

orbit

-0.64

 checkout

-0.63

wcs

-0.62

pload

-0.62

POSITIVE LOGITS

lene

0.69

achine

0.69

Vill

0.68

enegger

0.67

idis

0.63

entity

0.61

mercial

0.61

oon

0.61

assin

0.61

 ensemble

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.