INDEX

Explanations

medical terms related to specific types of cancers

oai_token-act-pair · gpt-3.5-turbo

references to health risks and diseases, particularly cancer

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

isan

-0.36

ADVERTISEMENT

-0.36

tm

-0.35

uchin

-0.35

kell

-0.34

osaurs

-0.34

 overseas

-0.34

azeera

-0.34

Opp

-0.34

ivated

-0.33

POSITIVE LOGITS

etheless

0.65

awaru

0.50

agall

0.48

 challeng

0.47

 Citiz

0.46

rul

0.45

ingen

0.44

 cryst

0.44

 antioxid

0.43

 tradem

0.41

Activations Density 1.990%

medical terms related to specific types of cancers

references to health risks and diseases, particularly cancer

No Comments

No Known Activations