INDEX

Explanations

indications of medical treatments or interventions

oai_token-act-pair · gpt-3.5-turbo

references to the act of taking medication or drugs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

unity

-0.84

Guy

-0.74

Pie

-0.70

wl

-0.67

Fans

-0.67

Mario

-0.65

hon

-0.65

Publisher

-0.65

PokÃ©mon

-0.64

nown

-0.64

POSITIVE LOGITS

 medication

1.13

 medications

1.10

 antidepressants

0.99

 antibiotics

0.96

 opioids

0.91

 prescription

0.89

 contraceptive

0.88

 insulin

0.87

 medicines

0.86

 drugs

0.86

Activations Density 0.242%

indications of medical treatments or interventions

references to the act of taking medication or drugs

No Comments

No Known Activations