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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

glers

-0.96

 satell

-0.75

FAT

-0.73

ngth

-0.71

 Eternity

-0.71

 accur

-0.69

eln

-0.68

qv

-0.66

igne

-0.65

atel

-0.65

POSITIVE LOGITS

 ÂŃ

0.70

asonry

0.66

lde

0.65

meric

0.65

ment

0.64

ism

0.62

mons

0.60

—-

0.59

condition

0.59

Shop

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.