INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

ased

-0.72

 sprung

-0.72

asing

-0.71

ntil

-0.70

é¾įå¥ĳå£«

-0.66

arb

-0.66

isoft

-0.66

 intrig

-0.66

 intrigue

-0.66

igg

-0.65

POSITIVE LOGITS

 ages

1.04

 Eliot

0.80

Sut

0.73

 Afric

0.71

Rus

0.69

 Russo

0.68

 Cathy

0.68

 Stamford

0.67

MRI

0.67

)</

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.