INDEX

Explanations

words related to physical and mental health issues, including symptoms, medical conditions, and side effects of medications

oai_token-act-pair · gpt-3.5-turbo

terms related to health conditions and their effects

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

soDeliveryDate

-0.95

deals

-0.79

çīĪ

-0.78

nesday

-0.74

roo

-0.74

solete

-0.73

Haunted

-0.71

trap

-0.69

DragonMagazine

-0.69

Deal

-0.69

POSITIVE LOGITS

 metabolism

1.31

 limbs

1.27

 functioning

1.21

 cognition

1.21

 consciousness

1.21

 mobility

1.20

 digestion

1.20

 thyroid

1.19

 bladder

1.18

 bowel

1.18

Activations Density 0.262%

words related to physical and mental health issues, including symptoms, medical conditions, and side effects of medications

terms related to health conditions and their effects

No Comments

No Known Activations