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

 Hispan

-0.80

itud

-0.79

UGE

-0.78

clusive

-0.74

¶æ

-0.72

 Akron

-0.68

clus

-0.68

¬¼

-0.65

 Hearts

-0.64

clusively

-0.64

POSITIVE LOGITS

haw

0.71

dain

0.70

wa

0.69

otto

0.69

paying

0.68

plementation

0.65

fly

0.64

eri

0.64

bugs

0.64

regular

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.