INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

bum

-0.77

=-=-=-=-=-=-=-=-

-0.72

pants

-0.71

 Rohing

-0.70

natureconservancy

-0.70

Wem

-0.69

amina

-0.69

malink

-0.68

_-

-0.67

Marco

-0.65

POSITIVE LOGITS

 capital

0.68

 Square

0.64

Square

0.63

 Ballard

0.62

itter

0.61

 custody

0.61

 leveled

0.61

 Controlled

0.61

 Morrow

0.59

 McCl

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.