INDEX

Explanations

terms related to medical symptoms

oai_token-act-pair · gpt-3.5-turbo

mentions of symptoms related to medical conditions

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

İ

-0.69

esan

-0.68

ISO

-0.67

lus

-0.64

company

-0.63

ombs

-0.62

yss

-0.62

vot

-0.62

olan

-0.61

berman

-0.61

POSITIVE LOGITS

ptoms

1.47

 Symptoms

1.19

 symptoms

1.18

igue

0.90

 symptom

0.87

olutions

0.86

 worsen

0.86

 ailments

0.82

 severity

0.80

igmatic

0.78

Activations Density 0.019%

terms related to medical symptoms

mentions of symptoms related to medical conditions

No Comments

No Known Activations