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

Vik

-0.67

ENT

-0.63

 Hawai

-0.61

 Singapore

-0.60

 Hyder

-0.60

 Hawaiian

-0.60

izabeth

-0.60

 Laur

-0.59

 Filip

-0.58

 innovate

-0.57

POSITIVE LOGITS

EStreamFrame

0.94

Ĥİ

0.87

Ń·

0.80

EStream

0.74

 Mechdragon

0.73

gran

0.73

idden

0.71

ģ«

0.71

aults

0.68

 Females

0.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.