INDEX

Explanations

phrases indicating actions or steps to be taken

oai_token-act-pair · gpt-3.5-turbo

imperative phrases or commands directed at the reader

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Preservation

-0.73

 Lori

-0.65

Offline

-0.63

 toughness

-0.63

natureconservancy

-0.62

 largeDownload

-0.61

 Nicole

-0.60

 Loren

-0.60

 Judd

-0.59

 Consortium

-0.59

POSITIVE LOGITS

 embark

0.89

isode

0.84

uberty

0.75

å£«

0.74

 proceed

0.73

dule

0.72

ABE

0.71

ividual

0.70

helm

0.70

olitics

0.70

Activations Density 0.071%

phrases indicating actions or steps to be taken

imperative phrases or commands directed at the reader

No Comments

No Known Activations