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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

isu

-0.74

etsy

-0.72

wrap

-0.71

 Percy

-0.71

Kos

-0.70

 Ples

-0.70

udeau

-0.69

meier

-0.69

etus

-0.66

quote

-0.65

POSITIVE LOGITS

¶æ

0.80

 PACs

0.74

otom

0.73

ocamp

0.70

Ĥª

0.69

uterte

0.65

ALD

0.64

ģ

0.64

ATT

0.63

ALTH

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.