INDEX

Explanations

terms related to medical conditions, specifically chronic ones

oai_token-act-pair · gpt-3.5-turbo

references to chronic conditions or illnesses

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

ramid

-0.93

*/(

-0.90

hammad

-0.80

ansk

-0.78

wagen

-0.76

animous

-0.74

imov

-0.73

ertodd

-0.73

Ĭ±

-0.72

ĪĴ

-0.70

POSITIVE LOGITS

 traumatic

0.86

led

0.83

 inflammation

0.80

 diseases

0.80

 chronic

0.79

ling

0.77

 disease

0.75

pain

0.74

ilitation

0.72

enter

0.72

Activations Density 0.017%

terms related to medical conditions, specifically chronic ones

references to chronic conditions or illnesses

No Comments

No Known Activations