INDEX

Explanations

references to a specific person named Kevin

oai_token-act-pair · gpt-3.5-turbo

instances of the name "Kevin."

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

schild

-0.86

yrinth

-0.83

pmwiki

-0.73

recomm

-0.69

bly

-0.68

mented

-0.68

MENTS

-0.67

paid

-0.65

minist

-0.65

stract

-0.64

POSITIVE LOGITS

 Rudd

0.88

arios

0.85

 Dunn

0.83

 Durant

0.82

 Bacon

0.82

 Faul

0.82

Kis

0.81

 Owens

0.80

 Harris

0.79

 Williamson

0.79

Activations Density 0.013%

references to a specific person named Kevin

instances of the name "Kevin."

No Comments

No Known Activations