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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

itcher

-0.75

 Patriarch

-0.71

 Oprah

-0.70

olean

-0.69

roid

-0.67

watch

-0.66

apy

-0.66

oaded

-0.66

haar

-0.65

heng

-0.65

POSITIVE LOGITS

IRE

0.82

urations

0.72

 sections

0.71

 footing

0.69

 Sections

0.67

 filing

0.67

cair

0.66

cule

0.65

ractions

0.63

 paragraphs

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.