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

igree

-0.83

eno

-0.74

onut

-0.72

estine

-0.70

eneg

-0.68

Saharan

-0.67

isations

-0.67

strip

-0.66

etooth

-0.66

>>\

-0.66

POSITIVE LOGITS

ÃŁ

0.72

terday

0.65

 stones

0.64

 Horizons

0.64

 Kund

0.63

Kuh

0.60

 imagination

0.59

Â·Â·

0.59

 stone

0.59

 eternal

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.