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

¶ħ

-0.73

bis

-0.73

avia

-0.66

esi

-0.64

book

-0.63

audi

-0.63

 Leilan

-0.63

 Anniversary

-0.62

 Norn

-0.62

Rai

-0.62

POSITIVE LOGITS

espie

0.75

 tabl

0.67

olver

0.66

 toget

0.64

ammers

0.64

multipl

0.62

 Liver

0.62

 Maver

0.61

urity

0.61

aghetti

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.