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

fram

-0.76

Sov

-0.72

amiya

-0.70

anca

-0.68

endas

-0.67

zona

-0.67

ikan

-0.66

Dial

-0.65

tsky

-0.65

 adjourn

-0.63

POSITIVE LOGITS

isters

0.68

 plurality

0.64

isively

0.62

 toxins

0.62

 flavours

0.62

soon

0.62

 colours

0.61

 supplies

0.61

wear

0.59

selves

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.