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

lihood

-0.83

yards

-0.83

eatures

-0.74

patch

-0.71

tool

-0.71

ibaba

-0.69

sense

-0.67

 aspirin

-0.67

meter

-0.67

rama

-0.66

POSITIVE LOGITS

atri

0.72

oi

0.72

sonian

0.68

EMBER

0.67

\\\\\\\\\\\\\\\\

0.66

ete

0.65

nton

0.64

ican

0.64

Universal

0.63

 Sagan

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.