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

iqueness

-0.71

 testimonies

-0.61

 aisle

-0.60

serving

-0.60

 CrossRef

-0.59

Customer

-0.59

 corners

-0.58

deen

-0.57

sci

-0.57

 SERV

-0.57

POSITIVE LOGITS

endi

0.78

pty

0.76

undown

0.71

agna

0.71

ope

0.68

hing

0.67

opes

0.66

urtle

0.65

apon

0.63

iple

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.