INDEX

Explanations

keywords related to programming and technical terms

oai_token-act-pair · gpt-3.5-turbo

indicators of statistical concepts and data analysis

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

artney

-0.79

infeld

-0.70

 blat

-0.69

eday

-0.68

 mosqu

-0.65

 adolesc

-0.60

ruce

-0.59

 gobl

-0.59

yip

-0.58

 thous

-0.58

POSITIVE LOGITS

 PTSD

0.52

 Shutterstock

0.51

CVE

0.50

 contagious

0.49

 exped

0.49

 vested

0.48

 lowered

0.47

 absence

0.47

 delayed

0.47

 otherwise

0.47

Activations Density 1.831%

keywords related to programming and technical terms

indicators of statistical concepts and data analysis

No Comments

No Known Activations