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

 destro

-0.74

ÄŁ

-0.69

ÅŁ

-0.67

 lockout

-0.67

 arrang

-0.65

 corrid

-0.65

 gobl

-0.63

fw

-0.63

owship

-0.63

Þ

-0.62

POSITIVE LOGITS

 Hodg

0.75

Yas

0.71

 Broad

0.68

Statistics

0.65

 Mous

0.65

Nob

0.65

 Converted

0.63

October

0.63

 Mans

0.63

 Ashley

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.