INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

quartered

-0.80

 dock

-0.72

ertodd

-0.71

 announce

-0.67

 settlements

-0.67

 suspect

-0.66

drop

-0.64

 drop

-0.64

 settle

-0.63

 shutter

-0.63

POSITIVE LOGITS

tions

0.77

Po

0.75

aria

0.74

ould

0.73

;;

0.73

Char

0.71

Solution

0.70

Ã«

0.69

Ãª

0.68

 Soup

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.