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

AA

-0.75

ordinary

-0.74

nces

-0.72

xual

-0.71

vention

-0.71

wcs

-0.71

 Occupations

-0.68

[&

-0.68

 encour

-0.66

à©

-0.62

POSITIVE LOGITS

 poisoning

0.72

onite

0.70

igon

0.69

 Madagascar

0.68

utenberg

0.68

 Naples

0.68

omach

0.67

 Newport

0.67

uba

0.67

oops

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.