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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

sale

-0.86

arge

-0.77

earch

-0.77

arf

-0.75

dain

-0.69

anish

-0.69

Mae

-0.68

ighed

-0.67

AMS

-0.67

rust

-0.67

POSITIVE LOGITS

 affairs

0.70

 tranqu

0.69

 Democr

0.68

 punct

0.66

 breeze

0.65

enegger

0.64

 tranquil

0.64

Vu

0.63

 favour

0.63

 opener

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.