INDEX

Explanations

words related to medications, prescriptions, and drug names

oai_token-act-pair · gpt-3.5-turbo

medical terms related to drugs and their classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ulty

-0.81

 Franchise

-0.80

selage

-0.79

isans

-0.78

rentices

-0.78

iqueness

-0.73

auga

-0.72

ourgeois

-0.72

 Buildings

-0.72

foundland

-0.72

POSITIVE LOGITS

 medications

1.59

 antidepressants

1.57

 medication

1.54

 aspirin

1.48

 pills

1.47

 chemotherapy

1.46

 antibiotics

1.46

 morphine

1.43

 opioids

1.42

 medicines

1.38

Activations Density 0.360%

words related to medications, prescriptions, and drug names

medical terms related to drugs and their classifications

No Comments

No Known Activations