INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

lied

-0.64

eco

-0.64

 Petra

-0.63

 adam

-0.61

Rom

-0.59

 Dove

-0.59

etr

-0.58

phi

-0.58

 Clarke

-0.57

 Bore

-0.57

POSITIVE LOGITS

algia

0.84

iversity

0.71

mails

0.68

¿

0.68

=~=~

0.67

 centr

0.66

acs

0.66

accompan

0.65

âĹ¼

0.65

NAS

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.