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

leasing

-0.79

LLP

-0.73

oway

-0.69

rooms

-0.65

atten

-0.65

 PACs

-0.64

leases

-0.61

 bluff

-0.60

 detachment

-0.60

shore

-0.60

POSITIVE LOGITS

zech

0.78

iere

0.76

arta

0.69

 dilig

0.66

 conclud

0.64

mone

0.64

grain

0.63

olkien

0.62

zek

0.62

Ott

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.