INDEX

Explanations

excerpts involving specific medical procedures or issues

oai_token-act-pair · gpt-3.5-turbo

references to relationships or connections between different entities or concepts

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

je

-0.56

abetes

-0.53

wcsstore

-0.52

dden

-0.47

 Belfast

-0.47

 Posted

-0.47

OPE

-0.46

 âĢº

-0.46

angering

-0.46

VIDEO

-0.46

POSITIVE LOGITS

 meanwhile

0.71

 moreover

0.69

 however

0.67

arger

0.59

 therefore

0.58

 furthermore

0.58

ogether

0.57

otomy

0.55

 though

0.49

 implies

0.48

Activations Density 2.710%

excerpts involving specific medical procedures or issues

references to relationships or connections between different entities or concepts

No Comments

No Known Activations