INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

oho

-0.84

ui

-0.76

undo

-0.76

yan

-0.75

ĸļ

-0.73

ibility

-0.73

orem

-0.72

hou

-0.71

bern

-0.70

Ord

-0.70

POSITIVE LOGITS

 incent

0.73

 inhibitor

0.71

 ancest

0.67

 reluct

0.65

 portals

0.64

 inhibitors

0.62

CLASSIFIED

0.62

ilogy

0.60

 certify

0.59

 phosphate

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.