INDEX

Explanations

long sequences of numbers alternating with text characters

oai_token-act-pair · gpt-3.5-turbo

references to performance metrics or criticisms of a document's content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

vantage

-0.77

zees

-0.71

rians

-0.70

aky

-0.70

blers

-0.70

Shift

-0.69

eden

-0.67

hesda

-0.67

ricular

-0.67

itto

-0.66

POSITIVE LOGITS

 letter

1.41

 manifesto

1.40

 memorandum

1.36

 article

1.34

 manuscript

1.32

 Declaration

1.32

 broch

1.30

 pamphlet

1.29

 paragraphs

1.28

 document

1.26

Activations Density 1.105%

long sequences of numbers alternating with text characters

references to performance metrics or criticisms of a document's content

No Comments

No Known Activations