INDEX

Explanations

technical and scientific terms related to various fields such as biology, medicine, and computer science

oai_token-act-pair · gpt-3.5-turbo

topics related to healthcare and medical conditions

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

 Vaugh

-0.65

>>>>>>>>

-0.51

 Mehran

-0.48

udos

-0.48

 Canaver

-0.48

 conclud

-0.46

eday

-0.46

 horizont

-0.45

theless

-0.45

nep

-0.45

POSITIVE LOGITS

picked

0.41

 household

0.39

 respective

0.38

 ancestor

0.38

opl

0.38

 industrial

0.38

 illustrious

0.37

frames

0.37

ims

0.36

zhou

0.36

Activations Density 2.532%

technical and scientific terms related to various fields such as biology, medicine, and computer science

topics related to healthcare and medical conditions

No Comments

No Known Activations