INDEX

Explanations

medical terms and entities related to healthcare administration

oai_token-act-pair · gpt-3.5-turbo

terms related to entities like patients, organizations, and data points within various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

Īè

-0.71

hots

-0.68

è£ħ

-0.66

»Ĵ

-0.65

ãĥĻ

-0.64

ãĤµ

-0.63

ildo

-0.62

hops

-0.62

cess

-0.61

)]

-0.61

POSITIVE LOGITS

's

1.24

 itself

1.23

ÃŃs

0.96

 playbook

0.89

 motto

0.88

 themselves

0.85

 penchant

0.83

 psyche

0.77

liest

0.76

 portion

0.76

Activations Density 0.638%

medical terms and entities related to healthcare administration

terms related to entities like patients, organizations, and data points within various contexts

No Comments

No Known Activations